© 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. 180535
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    communication, relationships, or actions

    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
     sponsors
    0.52
     reagents
    0.49
    ')[
    0.44
     Correction
    0.44
     riffs
    0.43
     electors
    0.43
    Correction
    0.43
     мүмк
    0.42
     órgãos
    0.42
     pesticides
    0.41
    POSITIVE LOGITS
    ኛ
    0.53
    בר
    0.50
    кия
    0.48
    OfDay
    0.48
     তো
    0.47
     Fecha
    0.47
    чний
    0.47
    大な
    0.46
     যেখানে
    0.46
     每个
    0.46
    Activations Density 0.000%

    No Known Activations