© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39917
    Prev
    Next
    INDEX
    Explanations

    required fields, asterisks

    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
     to
    -1.81
    centerTitle
    -1.16
    或
    -1.09
    }();
    -1.07
    mainAxisSize
    -1.05
     使用
    -1.03
     getHeight
    -1.02
    точный
    -1.00
    mpotent
    -0.99
    </tfoot>
    -0.99
    POSITIVE LOGITS
    ımız
    1.20
    Mikro
    1.14
    をご紹介
    1.12
     atún
    1.09
    眉头
    1.09
     szinte
    1.09
     megfe
    1.08
     たら
    1.05
     segíts
    1.05
     planificación
    1.04
    Activations Density 0.001%

    No Known Activations