© 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. 112105
    Prev
    Next
    INDEX
    Explanations

    or alternatives

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

    or or or

    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
    _
    0.50
    routine
    0.49
    ]=
    0.48
    кра
    0.48
    ча
    0.48
    тре
    0.48
    those
    0.47
    про
    0.46
    =
    0.46
    бо
    0.46
    POSITIVE LOGITS
     または
    0.57
    或者是
    0.55
     veya
    0.53
     yoki
    0.52
     અથવા
    0.52
     नवीनतम
    0.51
     alebo
    0.49
     durg
    0.48
     hoặc
    0.48
    または
    0.48
    Activations Density 0.001%

    No Known Activations