© 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. 22338
    Prev
    Next
    INDEX
    Explanations

    not only

    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
    ⃚
    -1.50
     Harian
    -1.49
    &
    -1.38
    Примеча
    -1.37
     chance
    -1.36
    哎呀
    -1.34
    itoriale
    -1.33
    Either
    -1.30
    isier
    -1.29
    كرت
    -1.29
    POSITIVE LOGITS
     —
    1.58
     were
    1.55
     TAMBIÉN
    1.46
    ção
    1.46
    quini
    1.41
     Exhibits
    1.41
    atação
    1.38
    tête
    1.37
    Cef
    1.35
    ены
    1.34
    Activations Density 0.007%

    No Known Activations