© 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. 203422
    Prev
    Next
    INDEX
    Explanations

    make one

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

    listing explanatory points

    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
     Membranes
    0.52
    from
    0.49
    sbin
    0.49
     Determining
    0.49
    SCC
    0.48
    прос
    0.47
    അ
    0.47
    Advanced
    0.46
    Strat
    0.46
     Ophthalmology
    0.46
    POSITIVE LOGITS
     recurrent
    0.59
     "
    0.56
     bah
    0.53
     transitory
    0.52
     "../../
    0.50
     hierarchy
    0.50
     recurring
    0.50
     m
    0.49
     jurídica
    0.49
     pertinentes
    0.49
    Activations Density 0.001%

    No Known Activations