© 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. 72933
    Prev
    Next
    INDEX
    Explanations

    how, below, about, tips, TO

    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
    廰
    -1.24
     historical
    -1.17
    べし
    -1.16
    敺
    -1.16
    歘
    -1.12
     hech
    -1.11
     Sane
    -1.11
     mogą
    -1.11
    橚
    -1.11
    新手
    -1.10
    POSITIVE LOGITS
    🛌
    1.30
    uw
    1.23
     in
    1.20
     lesz
    1.19
    </strong>
    1.16
    sukienka
    1.16
     ersten
    1.15
     všem
    1.13
     mendengarkan
    1.12
    läs
    1.10
    Activations Density 0.014%

    No Known Activations