© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19122
    Prev
    Next
    INDEX
    Explanations

    vanishing and banishing

    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
     posteriore
    -2.80
     ビキニ
    -2.72
     abbildung
    -2.72
    ㈯
    -2.66
     PLAYERS
    -2.64
    푔
    -2.63
     zitate
    -2.61
    삵
    -2.61
     copil
    -2.58
    despite
    -2.58
    POSITIVE LOGITS
     With
    2.91
    This
    2.81
    .
    2.63
     et
    2.55
     There
    2.52
     Here
    2.48
    …
    2.42
    </h2>
    2.41
     Using
    2.41
     These
    2.38
    Activations Density 0.004%

    No Known Activations