© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 173505
    Prev
    Next
    INDEX
    Explanations

    RG,THAT,more

    np_acts-logits-general · gemini-2.5-flash-lite

    configuration and system limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.59
    Mu
    0.50
    HP
    0.49
    Meter
    0.49
    el
    0.48
    LAS
    0.47
    Telex
    0.47
    Méd
    0.47
    льным
    0.47
    KY
    0.45
    POSITIVE LOGITS
     বণ্ট
    0.48
     دچار
    0.47
    ferenz
    0.46
     ફરિયા
    0.44
     днів
    0.43
     Loretta
    0.43
    俶
    0.42
    签署
    0.41
     उद्यमियों
    0.41
     ;,
    0.41
    Activations Density 0.001%

    No Known Activations