© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72153
    Prev
    Next
    INDEX
    Explanations

    ;} characters

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     {
    -2.50
    _{
    -2.39
     was
    -2.27
    an
    -2.17
    <em>
    -2.11
    いえば
    -2.06
     buscando
    -2.05
    providedIn
    -2.03
     tomando
    -2.02
     какой
    -2.00
    POSITIVE LOGITS
    ꦶ
    2.27
    ;}
    2.25
    __);
    2.16
    ꦫ
    2.13
    ї
    2.13
     něj
    2.11
    瘓
    2.11
    sibilidad
    2.09
    ,),
    2.08
    ymal
    2.08
    Activations Density 0.001%

    No Known Activations