© 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. 87994
    Prev
    Next
    INDEX
    Explanations

    home for, translate materials, face individuals, signed by

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

    domain, drives, remote, Michigan, ice

    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
     buradan
    0.55
     Press
    0.47
     sustit
    0.44
     medži
    0.44
    ভিং
    0.44
     redshift
    0.44
     Dred
    0.44
    ፕ
    0.43
     Segal
    0.43
     reading
    0.42
    POSITIVE LOGITS
    anyaan
    0.49
    이란
    0.48
    nur
    0.48
    atiu
    0.47
    atu
    0.46
    благо
    0.46
    一把
    0.46
    dzie
    0.46
    disabled
    0.46
    alin
    0.44
    Activations Density 0.000%

    No Known Activations