© 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. 237
    Prev
    Next
    INDEX
    Explanations

    Linked Open Data

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

    by + verb

    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
    ем
    0.61
    ет
    0.59
    Spell
    0.56
    Ꮿ
    0.55
    Risk
    0.53
    IAB
    0.53
    DAM
    0.52
     таком
    0.52
    он
    0.51
    ﻘ
    0.51
    POSITIVE LOGITS
    omatik
    0.48
     colouring
    0.46
     talents
    0.45
     rhubarb
    0.44
     habitats
    0.44
     nood
    0.43
     saffron
    0.43
     tsar
    0.43
    ogie
    0.43
     exam
    0.43
    Activations Density 0.000%

    No Known Activations