© 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. 196368
    Prev
    Next
    INDEX
    Explanations

    purpose because All

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

    limitations and errors

    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
    D
    0.52
    N
    0.49
    G
    0.49
     carc
    0.47
    MUST
    0.46
    ات
    0.46
    特
    0.46
    PC
    0.46
    NEW
    0.46
    ма
    0.46
    POSITIVE LOGITS
     Thánh
    0.54
     Accuracy
    0.52
    পুণ
    0.52
     হয়
    0.52
     Painters
    0.50
     Classifier
    0.49
    是一個
    0.49
     Sacrifice
    0.49
     Audience
    0.48
    rawberry
    0.48
    Activations Density 0.001%

    No Known Activations