© 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. 219497
    Prev
    Next
    INDEX
    Explanations

    people, places, or concepts

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

    explanations for specific concepts

    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
    這次
    0.52
    ᱷ
    0.50
    قبل
    0.49
    ﺧ
    0.47
    贖
    0.47
    ூன்
    0.46
    利亚
    0.45
     aprove
    0.45
    烪
    0.45
     respectivos
    0.45
    POSITIVE LOGITS
     Argument
    0.48
    textcolor
    0.47
     Birla
    0.46
     Gedanken
    0.45
     Jr
    0.45
     lumped
    0.45
    jt
    0.44
    マットレス
    0.44
    enerbah
    0.44
    &)
    0.44
    Activations Density 0.001%

    No Known Activations