© 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. 94972
    Prev
    Next
    INDEX
    Explanations

    crossroads , cmd

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

    proving

    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
    a
    0.52
     to
    0.50
    5
    0.50
     n
    0.50
     s
    0.49
     was
    0.49
     D
    0.48
    un
    0.47
     d
    0.47
     société
    0.46
    POSITIVE LOGITS
     কণ্
    0.53
    出発
    0.50
    比賽
    0.50
    iyasi
    0.50
    赛季
    0.49
    ியின்
    0.48
    い
    0.47
    ದಲ್ಲಿ
    0.47
    ಬಹುದು
    0.46
    ExpNow
    0.46
    Activations Density 0.002%

    No Known Activations