© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4192
    Prev
    Next
    INDEX
    Explanations

    CRM, databases, and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    unteers
    0.80
    待ち
    0.78
     mouths
    0.74
     stockings
    0.73
    ettings
    0.72
     ")");
    0.71
    ulation
    0.70
     $"{
    0.69
    apons
    0.68
    midd
    0.67
    POSITIVE LOGITS
     Delf
    2.83
    MAX
    2.74
     Nex
    2.72
    Mega
    2.71
     Athena
    2.71
     Zeus
    2.70
    SYS
    2.69
     Venus
    2.68
     Taurus
    2.68
     Apollo
    2.67
    Activations Density 1.432%

    No Known Activations