© 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. 50379
    Prev
    Next
    INDEX
    Explanations

    investor alert by

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

    Handles requests or incoming data

    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
    Louise
    0.47
     versionName
    0.45
    Aye
    0.45
     anlaş
    0.44
    㥳
    0.43
    opoulos
    0.43
     változat
    0.43
     препят
    0.43
    ير
    0.42
    Automatic
    0.42
    POSITIVE LOGITS
     frontal
    0.45
     கட்ட
    0.45
     ਮ
    0.45
     synthes
    0.44
     lij
    0.44
    ۔
    0.43
     seconded
    0.43
     hotly
    0.43
     fasted
    0.43
     peter
    0.43
    Activations Density 0.000%

    No Known Activations