© 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. 84612
    Prev
    Next
    INDEX
    Explanations

    in this

    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
    Not in Any Lists

    No Comments

    Negative Logits
     őket
    -1.63
    怀里
    -1.55
    复活
    -1.52
     modalidad
    -1.52
     ausser
    -1.48
     utiliser
    -1.47
    ֶּ
    -1.46
     sosteniendo
    -1.45
     egyéb
    -1.44
     pantalón
    -1.43
    POSITIVE LOGITS
     and
    1.69
    taya
    1.66
    
    1.61
    +
    1.55
     zahlreichen
    1.53
    yos
    1.47
     kurikulum
    1.43
    ጺ
    1.41
     when
    1.39
    pherical
    1.39
    Activations Density 0.052%

    No Known Activations