© 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. 195001
    Prev
    Next
    INDEX
    Explanations

    media upload and options

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

    more concise

    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
    old
    0.50
    workshop
    0.48
    HttpSession
    0.48
    πο
    0.46
    apply
    0.46
    ʊ
    0.45
    close
    0.45
    盲
    0.45
    tun
    0.45
    adjust
    0.44
    POSITIVE LOGITS
     Sterne
    0.49
     Wert
    0.49
     expl
    0.48
     Food
    0.46
     አስተ
    0.46
     FOOD
    0.45
     மதிப்ப
    0.44
     Zou
    0.43
     comest
    0.43
     She
    0.43
    Activations Density 0.002%

    No Known Activations