© 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. 31336
    Prev
    Next
    INDEX
    Explanations

    Tai Chi classes, equipment, mines, sideboards

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

    solutions and methods

    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
    İY
    0.39
    __(/*!
    0.38
    蒟
    0.38
    Después
    0.37
    ⴼ
    0.37
    ēc
    0.35
    itabbo
    0.35
    ็ต
    0.35
    𝒇
    0.35
    朓
    0.35
    POSITIVE LOGITS
     gerne
    0.44
    incs
    0.40
    heh
    0.40
    мер
    0.40
    供应
    0.40
     diese
    0.37
    folge
    0.37
    ைய
    0.37
    anga
    0.37
     Offices
    0.36
    Activations Density 0.000%

    No Known Activations