© 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. 162877
    Prev
    Next
    INDEX
    Explanations

    language specification

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

    interstellar identification and adjustment

    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
     beams
    0.48
     horseradish
    0.47
    ’
    0.46
     repeated
    0.46
     vanishes
    0.46
     hypoxic
    0.46
     reactive
    0.45
     flown
    0.44
     minimizes
    0.44
     prohibits
    0.43
    POSITIVE LOGITS
     allgemein
    0.48
     abbiamo
    0.47
     Κ
    0.46
     শিশুরা
    0.46
    izzate
    0.45
    letos
    0.45
     ആയി
    0.44
     জেনে
    0.44
     স্বভাব
    0.44
     اعرف
    0.44
    Activations Density 0.000%

    No Known Activations