© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111669
    Prev
    Next
    INDEX
    Explanations

    biographies of individuals

    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
    咂
    -1.75
    prender
    -1.63
     you
    -1.52
    −/−
    -1.50
     обратиться
    -1.45
    焼肉
    -1.44
     собрать
    -1.42
    今年は
    -1.41
    ligere
    -1.36
     подобрать
    -1.35
    POSITIVE LOGITS
     had
    1.88
     from
    1.77
    していました
    1.45
     of
    1.41
    (!__
    1.34
    })\
    1.33
     at
    1.32
     with
    1.32
    してました
    1.32
    conomie
    1.30
    Activations Density 0.072%

    No Known Activations