© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106672
    Prev
    Next
    INDEX
    Explanations

    version numbers or time

    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_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
     NRA
    -0.72
    buru
    -0.70
     Newer
    -0.69
    americanas
    -0.69
    israel
    -0.68
    NRA
    -0.67
     eingeführt
    -0.66
    antle
    -0.65
    lared
    -0.65
    avu
    -0.65
    POSITIVE LOGITS
    ēs
    0.72
     adapté
    0.71
     Chinois
    0.69
     FACTORS
    0.69
    ició
    0.69
     ブラウン
    0.68
    メル
    0.68
     disorders
    0.68
     Etudes
    0.67
    REM
    0.66
    Activations Density 0.026%

    No Known Activations