© 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. 222611
    Prev
    Next
    INDEX
    Explanations

    local law or box below

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

    those wanting

    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
    ا
    0.48
    කාශ
    0.47
     Freizeit
    0.45
    irtschaft
    0.44
    querySelectorAll
    0.42
     monotonically
    0.42
     contag
    0.41
    िया
    0.41
     propriétaire
    0.40
    in
    0.39
    POSITIVE LOGITS
    Ｚ
    0.52
    award
    0.48
    数値
    0.47
    findings
    0.47
     karoti
    0.47
    discover
    0.47
     honti
    0.46
     उसमें
    0.46
    DROP
    0.46
    flip
    0.46
    Activations Density 0.000%

    No Known Activations