© 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. 201486
    Prev
    Next
    INDEX
    Explanations

    mine out; November trade

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

    weather and seasons

    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
    ał
    0.69
    ił
    0.54
    unca
    0.51
    apoptotic
    0.49
    playerName
    0.48
    currentToken
    0.48
    ł
    0.47
    łka
    0.47
    awać
    0.46
    hydrogen
    0.45
    POSITIVE LOGITS
     Looking
    0.54
     Posts
    0.51
     Families
    0.49
     Owners
    0.49
     Smack
    0.48
     Tenants
    0.47
     People
    0.46
    嘮
    0.46
    娛
    0.46
     City
    0.46
    Activations Density 0.000%

    No Known Activations