© 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. 40878
    Prev
    Next
    INDEX
    Explanations

    locations with 'Co.'

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

    subqueries and parentheses

    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
    ेलर
    0.47
    дан
    0.43
    सास
    0.43
    MP
    0.42
     பரபர
    0.42
    до
    0.42
    例文
    0.42
    千
    0.41
    OLA
    0.41
    п
    0.41
    POSITIVE LOGITS
     Gambia
    0.49
     Decoding
    0.48
    ে
    0.47
     MRS
    0.44
     EQUIPMENT
    0.44
     Monsanto
    0.44
     Mane
    0.44
     Vishal
    0.44
     Defined
    0.43
     bringing
    0.43
    Activations Density 0.000%

    No Known Activations