© 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. 142331
    Prev
    Next
    INDEX
    Explanations

    your copy

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

    anniversary visitors benefits amused growth

    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
    Prog
    0.51
    eau
    0.48
    踪
    0.46
    ნობ
    0.45
    zept
    0.44
    umb
    0.43
    厅
    0.43
    <0x0D>
    0.43
     Prog
    0.42
    каз
    0.42
    POSITIVE LOGITS
     පේශ
    0.45
     berdoa
    0.45
     antecedent
    0.44
    oluminescence
    0.44
     شکار
    0.44
     ત્યારે
    0.43
     všech
    0.43
     Predicted
    0.43
     takut
    0.43
     ભાવ
    0.43
    Activations Density 0.001%

    No Known Activations