© 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. 210862
    Prev
    Next
    INDEX
    Explanations

    third plot, payment card, African American

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

    status, requirement, or decision

    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
     plans
    0.52
     愛
    0.52
    ନ୍ତ
    0.52
    instellungen
    0.50
     Процитовано
    0.50
     Україн
    0.49
     emotions
    0.49
     obligations
    0.48
     investments
    0.47
    in
    0.47
    POSITIVE LOGITS
    委员
    0.45
    சாமி
    0.42
    дия
    0.41
     szerző
    0.41
    ادي
    0.40
    향
    0.40
    randomIndex
    0.40
    GUI
    0.40
    тори
    0.40
     linestyle
    0.40
    Activations Density 0.000%

    No Known Activations