© 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. 1148
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

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

    concepts and states

    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
    （
    0.53
     on
    0.52
    、
    0.51
    ，
    0.50
     и
    0.50
    (\
    0.50
    /
    0.45
     và
    0.44
    (
    0.43
    や
    0.42
    POSITIVE LOGITS
     Ather
    0.45
    摭
    0.43
     Brilliant
    0.42
     রাধানাথ
    0.41
     শ্বাস
    0.40
     Григо
    0.40
     బ్రిటిష్
    0.40
     Caed
    0.40
     Архи
    0.40
    ˮ
    0.39
    Activations Density 0.000%

    No Known Activations