© 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. 67275
    Prev
    Next
    INDEX
    Explanations

    Molly followed by surname

    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
     was
    -2.63
    ar
    -2.20
    т
    -2.14
    e
    -2.11
    க்
    -2.08
     другие
    -2.08
    镚
    -2.08
    个月
    -2.06
     passione
    -2.06
    飈
    -1.99
    POSITIVE LOGITS
    凄く
    2.52
     They
    2.48
    ⡃
    2.39
     entspre
    2.38
    CurtirCurtir
    2.34
     eigener
    2.33
    荭
    2.30
    鱨
    2.22
     zusätz
    2.20
    蜮
    2.20
    Activations Density 0.007%

    No Known Activations