© 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. 172415
    Prev
    Next
    INDEX
    Explanations

    BIO, since, Broch

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

    preventing healthcare overload

    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
    Č
    0.53
    ليم
    0.51
    Ç
    0.50
    ﻤ
    0.50
    Número
    0.49
     中心
    0.49
    مركز
    0.48
    لیم
    0.48
    ポイント
    0.47
    𝗦
    0.47
    POSITIVE LOGITS
    visions
    0.53
     mattis
    0.46
    ithe
    0.44
    ята
    0.44
     hent
    0.43
    тел
    0.42
    ar
    0.42
     Jenny
    0.42
    atória
    0.42
    vasive
    0.41
    Activations Density 0.000%

    No Known Activations