© 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. 117802
    Prev
    Next
    INDEX
    Explanations

    critical distribution

    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
     down
    -0.72
     skall
    -0.69
     off
    -0.68
    ffing
    -0.64
     temps
    -0.64
     reference
    -0.63
    ABORT
    -0.63
     inneren
    -0.62
    sigue
    -0.62
    freed
    -0.62
    POSITIVE LOGITS
    lanco
    0.80
    seido
    0.75
     Cuenca
    0.71
    jutkan
    0.71
    ragment
    0.71
    の形
    0.70
    __*/
    0.68
    <0xA1>
    0.68
     Mackey
    0.68
    extAlignment
    0.68
    Activations Density 0.040%

    No Known Activations