© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3703
    Prev
    Next
    INDEX
    Explanations

    (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    łaś
    1.83
     izol
    1.78
     класс
    1.64
    واصل
    1.63
     separar
    1.62
    處
    1.61
    处
    1.60
     كلهم
    1.59
     włos
    1.58
     indywidual
    1.57
    POSITIVE LOGITS
     (
    3.52
    （
    3.04
    (
    2.93
     ((
    2.88
     ([
    2.65
     (‘
    2.64
    ((
    2.62
     (`
    2.59
     ($\
    2.53
     (\
    2.53
    Activations Density 0.271%

    No Known Activations