© 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. 10-GEMMASCOPE-RES-131K
    7. 59458
    Prev
    Next
    INDEX
    Explanations

    samples taken for testing

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

    references to biological samples being collected, taken, or analyzed.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     {
    -1.41
    :{
    -1.40
    一些
    -1.39
    we
    -1.30
    f
    -1.27
    .
    -1.23
    V
    -1.22
    4
    -1.21
    france
    -1.20
    ２
    -1.20
    POSITIVE LOGITS
     generalmente
    1.64
    おわりに
    1.48
     oscuridad
    1.45
     duża
    1.42
    .''
    1.42
    erráneo
    1.41
     meestal
    1.40
     that
    1.39
     поэтому
    1.38
     his
    1.34
    Activations Density 0.092%

    No Known Activations