© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7337
    Prev
    Next
    INDEX
    Explanations

    public, http, panic, header, value

    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
    スポンサーリンク
    -2.42
    他已经
    -2.34
    さてさて
    -2.30
    暑い
    -2.22
    子供が
    -2.19
    </sup>
    -2.19
    昔から
    -2.16
    蓠
    -2.14
    というわけで
    -2.14
    他有
    -2.11
    POSITIVE LOGITS
     vorigen
    3.63
     worin
    2.81
    щита
    2.70
    褙
    2.66
    𔘓
    2.55
    इटम
    2.53
     Zweiten
    2.44
     englischen
    2.28
     andet
    2.27
    遯
    2.25
    Activations Density 0.029%

    No Known Activations