© 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. 26984
    Prev
    Next
    INDEX
    Explanations

    cleaning brush; to help; an extruded

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

    concise statements or summaries

    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
     Caves
    0.46
    南
    0.46
    沉
    0.44
    需要
    0.44
    知道
    0.43
    至
    0.42
     dumb
    0.42
    糟
    0.42
     potenti
    0.41
    CHAN
    0.41
    POSITIVE LOGITS
    𝒚
    0.48
    મારી
    0.46
     മുഖ്യമ
    0.45
     สม
    0.44
     இடத்தில்
    0.44
     Бан
    0.44
     ভালবাস
    0.44
     hạnh
    0.43
     سپورټ
    0.42
     Balliye
    0.42
    Activations Density 0.000%

    No Known Activations