© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42924
    Prev
    Next
    INDEX
    Explanations

    cool slang adjectives

    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
    ℣
    -1.65
     involucrados
    -1.56
     beliebtesten
    -1.46
    𖤣
    -1.44
     sélectionner
    -1.42
    就跟
    -1.39
     verschieden
    -1.38
     timmar
    -1.36
     aislados
    -1.35
     ajoutez
    -1.34
    POSITIVE LOGITS
     if
    1.35
    ("
    1.34
     and
    1.34
     двумя
    1.34
    </b>
    1.33
    icação
    1.31
    台風
    1.31
    坤
    1.30
    ),
    1.30
     new
    1.29
    Activations Density 0.044%

    No Known Activations