© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91381
    Prev
    Next
    INDEX
    Explanations

    version numbers or software terms

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

    The neuron fires on code‐style identifiers and metadata tokens (e.g. “Debug”, “exec”, version or license numbers, “unicode_name”, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    诣
    -0.90
     Nightmare
    -0.81
    utile
    -0.70
     KICK
    -0.70
    itana
    -0.70
    מונות
    -0.70
    inine
    -0.69
    冠軍
    -0.69
     Thompson
    -0.68
     ponsel
    -0.68
    POSITIVE LOGITS
     braccia
    0.68
     độc
    0.67
    вают
    0.67
     حسب
    0.66
    KILL
    0.65
    Ж
    0.65
    記
    0.65
     SF
    0.64
    VII
    0.63
     ويع
    0.63
    Activations Density 0.025%

    No Known Activations