© 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. 220409
    Prev
    Next
    INDEX
    Explanations

    business, cities, branding, hunter

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

    sections, imperfections, specific, clothing

    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
     scrive
    0.50
    থাৎ
    0.47
    宪
    0.46
    igence
    0.46
     служит
    0.45
     humiliation
    0.45
    出した
    0.44
    出して
    0.44
     déput
    0.44
     ചിത്ര
    0.44
    POSITIVE LOGITS
    yaa
    0.50
    \
    0.48
    hoes
    0.47
     Pred
    0.46
    bari
    0.44
    hack
    0.44
    annon
    0.43
    kij
    0.43
    bie
    0.43
    kaan
    0.43
    Activations Density 0.000%

    No Known Activations