© 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. 34-GEMMASCOPE-RES-131K
    4. 49978
    Prev
    Next
    INDEX
    Explanations

    static code keyword

    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_34/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
     still
    -0.88
    リーム
    -0.86
     accompanied
    -0.85
     Cracker
    -0.83
     diventato
    -0.81
     seule
    -0.76
    indsay
    -0.76
    stered
    -0.76
    maids
    -0.75
     bandage
    -0.75
    POSITIVE LOGITS
     minOccurs
    1.16
    ally
    1.13
     Static
    0.98
    ALLY
    0.88
    Intended
    0.87
     propTypes
    0.86
     AssemblyVersion
    0.86
    œ
    0.85
    MetaObject
    0.85
    ktes
    0.85
    Activations Density 0.008%

    No Known Activations