© 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. 121939
    Prev
    Next
    INDEX
    Explanations

    release, popular, bless, mystery, and, anti, paper, supporters

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

    instructions and descriptions

    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
     dusted
    0.50
    Analog
    0.49
    ούς
    0.48
    ర్శ
    0.48
     Analog
    0.48
     seductive
    0.47
    镓
    0.47
     objet
    0.46
    Hayes
    0.46
    嫄
    0.46
    POSITIVE LOGITS
    cektir
    0.51
    lu
    0.49
    ktir
    0.49
    gn
    0.48
    gz
    0.48
    lock
    0.48
    vek
    0.47
    yemek
    0.47
    besch
    0.47
     സ്ഥി
    0.47
    Activations Density 0.001%

    No Known Activations