© 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. 104025
    Prev
    Next
    INDEX
    Explanations

    archival collections

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

    Ensures, societal, Mycenaean, OG image

    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
     האי
    0.59
     مُ
    0.57
     المُ
    0.54
     روم
    0.52
     الإ
    0.51
    rü
    0.51
     المه
    0.51
     النظام
    0.51
     الشي
    0.50
     ਸ਼
    0.50
    POSITIVE LOGITS
    いろいろ
    0.46
    स्पर्
    0.45
     tireless
    0.45
     `>`,
    0.44
    体
    0.44
    髪
    0.44
    យក
    0.43
    謾
    0.43
    もう
    0.43
    LEAR
    0.42
    Activations Density 0.000%

    No Known Activations