© 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. 145692
    Prev
    Next
    INDEX
    Explanations

    legal proceedings

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

    evocative writing and ukulele music

    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
    онов
    0.48
    revoke
    0.48
    מיני
    0.47
    rowad
    0.46
     самым
    0.46
    궪
    0.46
    álním
    0.46
    étiques
    0.45
    ከሰ
    0.45
    हित
    0.45
    POSITIVE LOGITS
     ea
    0.46
     a
    0.44
     diffraction
    0.42
     ühe
    0.41
     an
    0.41
     seco
    0.41
     point
    0.40
     einer
    0.40
     eddies
    0.40
     O
    0.40
    Activations Density 0.000%

    No Known Activations