© 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. 99924
    Prev
    Next
    INDEX
    Explanations

    family and friends

    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
     parámetros
    -1.84
     apenas
    -1.73
     créer
    -1.73
    
    -1.61
    ῃ
    -1.61
     faciliter
    -1.60
     choisir
    -1.58
     فقط
    -1.56
     obtenir
    -1.56
     propriedades
    -1.55
    POSITIVE LOGITS
     many
    2.63
     during
    2.53
     had
    2.48
     and
    2.45
     our
    2.42
     my
    2.28
     three
    2.23
     took
    2.16
     also
    2.14
     several
    2.11
    Activations Density 0.015%

    No Known Activations