© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 31639
    Prev
    Next
    INDEX
    Explanations

    LZW encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сть
    0.39
    Payload
    0.39
    ReLU
    0.39
    relu
    0.38
    োম
    0.38
    permission
    0.38
    converted
    0.37
    弥
    0.37
    payload
    0.37
     converting
    0.37
    POSITIVE LOGITS
     match
    0.51
    eof
    0.46
     Literal
    0.44
    Huff
    0.43
     Match
    0.43
     window
    0.43
    窗口
    0.43
     MATCH
    0.42
     alfabet
    0.42
     matches
    0.41
    Activations Density 0.004%

    No Known Activations