© 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. 22-GEMMASCOPE-RES-131K
    7. 16264
    Prev
    Next
    INDEX
    Explanations

    i.e. clarification

    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_22/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
     хорошо
    -1.78
    tembro
    -1.74
    aneity
    -1.70
     জন্য
    -1.66
    ’,
    -1.65
    }$.
    -1.65
    ンの
    -1.63
    镭
    -1.63
     姆
    -1.63
    ’).
    -1.62
    POSITIVE LOGITS
    "
    2.31
    '
    2.25
    ,
    2.16
    有些不
    1.61
     colombiana
    1.56
     aktive
    1.55
     Nedir
    1.53
     majeurs
    1.49
     étr
    1.48
     kimdir
    1.48
    Activations Density 0.024%

    No Known Activations