© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91900
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     Milo
    -0.85
    CDN
    -0.85
    mila
    -0.84
    RIK
    -0.84
     CHAPITRE
    -0.82
    ojo
    -0.82
    部分は
    -0.81
    িয়ে
    -0.81
    KYO
    -0.80
    ^*$
    -0.80
    POSITIVE LOGITS
     Application
    1.34
     Mathf
    1.30
     Random
    1.26
     Time
    1.23
    Math
    1.23
    Application
    1.21
     Input
    1.10
    Random
    1.03
     transform
    1.00
    Input
    0.98
    Activations Density 0.003%

    No Known Activations