© 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. 151698
    Prev
    Next
    INDEX
    Explanations

    geographic entities and specific nouns

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

    growing tech scene liquid composition

    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
     аппара
    0.53
     REGIUNI
    0.52
     נ
    0.51
     SPARSE
    0.51
     COMPARE
    0.51
     cui
    0.51
     אני
    0.51
    仠
    0.50
     bilj
    0.50
     來
    0.50
    POSITIVE LOGITS
    IDs
    0.55
    birth
    0.54
    blow
    0.49
    book
    0.48
    qw
    0.47
    transmission
    0.47
    ert
    0.47
    ashing
    0.47
    Data
    0.46
    Blo
    0.46
    Activations Density 0.000%

    No Known Activations