© 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. 24594
    Prev
    Next
    INDEX
    Explanations

    easy to use or manage

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

    connectors, cables, and configuration

    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
     someone
    0.49
     BRE
    0.48
    someone
    0.47
    bre
    0.45
    0.45
    °
    0.45
     Someone
    0.44
     “
    0.44
     bre
    0.43
     W
    0.41
    POSITIVE LOGITS
     drücken
    0.53
    ColumnKind
    0.52
    MathMarks
    0.49
     också
    0.49
     assolutamente
    0.49
    üğünüz
    0.48
     säker
    0.48
    WinCounter
    0.48
     vaše
    0.47
     ক্রিকে
    0.47
    Activations Density 0.018%

    No Known Activations