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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12366
    Prev
    Next
    INDEX
    Explanations

    personal situation or experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Æ
    -0.79
    是对
    -0.78
     Nullable
    -0.78
    Actin
    -0.75
    发表于
    -0.74
    Af
    -0.74
    shire
    -0.74
     limone
    -0.74
     châ
    -0.73
     Dipl
    -0.73
    POSITIVE LOGITS
     personally
    1.04
     or
    0.94
    ligheter
    0.84
    erts
    0.79
    etermined
    0.79
    ảng
    0.79
    Retorno
    0.77
     ukon
    0.77
    myself
    0.76
    lň
    0.75
    Activations Density 0.099%

    No Known Activations