© 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. 197101
    Prev
    Next
    INDEX
    Explanations

    manufacturing jobscare servicelinked directlyproduce lightmap outseason

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

    lists, clauses, and punctuation

    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
    朓
    0.53
     אך
    0.51
    éfono
    0.50
     hoogte
    0.49
     बीसीजी
    0.49
     Fälle
    0.48
     oblasti
    0.48
    ข้อง
    0.47
     ताम
    0.47
    崤
    0.47
    POSITIVE LOGITS
    _
    0.59
    +
    0.57
    uy
    0.56
    ay
    0.56
    -
    0.55
    {
    0.55
    ю
    0.53
    !
    0.51
    ah
    0.49
    ?
    0.49
    Activations Density 0.000%

    No Known Activations