© 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. 64315
    Prev
    Next
    INDEX
    Explanations

    rights reserved

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

    talking about options

    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
     Martha
    0.45
    ლებიც
    0.45
    🏁
    0.45
    賖
    0.45
     Cayman
    0.44
     Tall
    0.44
     Hosp
    0.44
    ティー
    0.43
    tall
    0.43
     علاوہ
    0.43
    POSITIVE LOGITS
     टूटा
    0.48
    ຫານ
    0.47
     plunged
    0.46
    ‘
    0.46
    quant
    0.44
     progenitors
    0.44
    ın
    0.43
    こうした
    0.43
     effectually
    0.42
    Khi
    0.41
    Activations Density 0.000%

    No Known Activations