© 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. 31779
    Prev
    Next
    INDEX
    Explanations

    until a specific state

    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
     assust
    -0.92
     onPause
    -0.92
     BitmapFactory
    -0.87
    atifying
    -0.86
    ppling
    -0.85
     higher
    -0.85
    asting
    -0.85
    ഢ
    -0.84
     Vielzahl
    -0.84
     ESTADO
    -0.84
    POSITIVE LOGITS
    大部分
    1.18
     completely
    1.13
     no
    1.08
     they
    1.05
     until
    1.04
     thoroughly
    1.04
     you
    1.01
    完全
    1.00
     tất
    0.96
    所有的
    0.96
    Activations Density 0.012%

    No Known Activations