© 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. 52399
    Prev
    Next
    INDEX
    Explanations

    quoted text followed by semicolon

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

    HTML entities, URL encoding

    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
    ale
    0.65
    ac
    0.58
    سل
    0.56
    به
    0.56
    un
    0.55
    c
    0.55
    ade
    0.55
    ک
    0.55
    ان
    0.54
    ál
    0.54
    POSITIVE LOGITS
    izamos
    0.62
     piggy
    0.59
    <0x80>
    0.55
     appease
    0.54
     chuyển
    0.52
     manipulate
    0.52
    ;|&
    0.52
     simple
    0.51
     rearrange
    0.51
     recyclable
    0.51
    Activations Density 0.012%

    No Known Activations