© 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. 147895
    Prev
    Next
    INDEX
    Explanations

    indoor or outdoor

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

    describing or contrasting 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
     in
    0.57
    ジャ
    0.54
    ขา
    0.54
    স
    0.52
    ใน
    0.50
    [
    0.50
    ह
    0.49
    >
    0.49
    수는
    0.48
    новых
    0.48
    POSITIVE LOGITS
    anton
    0.47
     நகை
    0.46
    aset
    0.45
     disgraceful
    0.44
    tipped
    0.44
    achim
    0.44
    arantad
    0.43
     संतोष
    0.43
    喜剧
    0.43
    construct
    0.42
    Activations Density 0.000%

    No Known Activations