© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14210
    Prev
    Next
    INDEX
    Explanations

    Neurokinin or Metastatic

    np_acts-logits-general · gemini-2.5-flash-lite

    special characters in cryptographic and technical contexts, particularly numeric values and symbols like +, /, †, and ‡.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on the non-letter symbols and digits typical of Base64-encoded blocks (e.g. “+”, “/”, and numerals) as seen in the RSA key data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最重要
    -1.84
    ción
    -1.80
    琤
    -1.60
    ↵↵
    -1.59
     Для
    -1.57
    ты
    -1.50
    摶
    -1.49
    ´
    -1.48
     When
    -1.48
     esencial
    -1.48
    POSITIVE LOGITS
    蔸
    1.91
    if
    1.72
     $-$
    1.72
     loosing
    1.66
    卺
    1.66
    茕
    1.65
    虽
    1.64
    by
    1.63
    χεία
    1.60
    簟
    1.59
    Activations Density 0.002%

    No Known Activations