© 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. 220446
    Prev
    Next
    INDEX
    Explanations

    legal proceedings, decisions, or rulings

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

    list and its follow-up items

    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
    ਰ
    0.52
    ラップ
    0.52
    richtungen
    0.50
    rektor
    0.50
     ነገ
    0.50
    льше
    0.49
    ל
    0.48
     almac
    0.48
    ૩
    0.47
    Mogo
    0.47
    POSITIVE LOGITS
     a
    0.48
     Chanc
    0.48
     Dw
    0.47
     Phyl
    0.46
     Venue
    0.46
     Areas
    0.46
     Sources
    0.45
     Whilst
    0.44
     References
    0.44
     Modules
    0.44
    Activations Density 0.001%

    No Known Activations