© 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. 14526
    Prev
    Next
    INDEX
    Explanations

    sports news and seasons

    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
     of
    -1.70
     either
    -1.36
     from
    -1.36
    zbęd
    -1.32
     використо
    -1.30
     unspeak
    -1.30
     Física
    -1.24
     uitzicht
    -1.23
    postolic
    -1.23
     вона
    -1.22
    POSITIVE LOGITS
    で
    1.25
    Descriere
    1.20
    での
    1.15
     berbagai
    1.12
    」、
    1.07
     чего
    1.06
    那么
    1.05
    を
    1.04
     englisch
    1.04
     mengumumkan
    1.04
    Activations Density 0.195%

    No Known Activations