© 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. 50201
    Prev
    Next
    INDEX
    Explanations

    multilingual entities and individuals

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

    non-English characters and timestamps

    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
     summarised
    0.48
    जैसा
    0.46
     mises
    0.45
     signatories
    0.45
    𒁳
    0.45
     paziente
    0.44
     conoscenza
    0.44
     emphasise
    0.43
     capsule
    0.43
     conventionally
    0.43
    POSITIVE LOGITS
     و
    0.53
    ي
    0.51
    orpion
    0.44
    rates
    0.44
     व
    0.44
    ে
    0.43
    我
    0.43
    massage
    0.42
    罵
    0.42
    は
    0.41
    Activations Density 0.000%

    No Known Activations