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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33345
    Prev
    Next
    INDEX
    Explanations

    return / output links

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

    the neuron fires on code‐like structural tokens—labels, keywords, and symbols used in programming or configuration contexts (for example, field names or braces and colons).

    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
    Shown
    -0.72
    Ben
    -0.68
    Containing
    -0.66
    ↰
    -0.65
     Vs
    -0.65
    Btn
    -0.65
     ecological
    -0.64
    Check
    -0.64
    経験
    -0.64
    Vs
    -0.63
    POSITIVE LOGITS
    obald
    0.84
     フラワー
    0.83
    anything
    0.79
    valbard
    0.76
    EARCH
    0.75
    bles
    0.74
    direc
    0.73
    诃
    0.72
    правление
    0.71
     vigencia
    0.71
    Activations Density 0.028%

    No Known Activations