© 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. 8221
    Prev
    Next
    INDEX
    Explanations

    names, places, numbers

    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
    …»
    -1.15
     "));
    -1.10
     THIS
    -1.10
     misma
    -1.09
     mismo
    -1.09
     an
    -1.09
     МО
    -1.09
     petani
    -1.09
     spielte
    -1.08
    ...»
    -1.08
    POSITIVE LOGITS
     Gorbachev
    1.18
     occup
    1.17
    توضیحات
    1.16
    ⼈
    1.10
     inappropri
    1.09
    _
    1.08
     Cassette
    1.06
    akor
    1.05
    ГЛА
    1.05
    蒟
    1.05
    Activations Density 0.701%

    No Known Activations