© 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. 14250
    Prev
    Next
    INDEX
    Explanations

    certainly, very, too

    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
     or
    -1.55
    kast
    -1.11
    atok
    -1.09
    يًا
    -1.08
    şk
    -1.07
     a
    -1.07
    casts
    -1.05
    荇
    -1.05
    螨
    -1.03
    يا
    -1.02
    POSITIVE LOGITS
     but
    1.65
     still
    1.33
    kregen
    1.20
    けど
    1.15
     impactos
    1.14
    
    1.13
     estí
    1.13
    を見た
    1.13
     eficacia
    1.12
     equally
    1.11
    Activations Density 0.073%

    No Known Activations