© 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. 244063
    Prev
    Next
    INDEX
    Explanations

    positive feedback or win

    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
    ಳ್ಳ
    0.50
    started
    0.50
     風
    0.46
    賚
    0.46
    ὥ
    0.46
    長
    0.45
     勝
    0.45
    ರ್ಮ
    0.45
    OFFSET
    0.45
     薄
    0.45
    POSITIVE LOGITS
    ้น
    0.44
    व्स
    0.43
     trending
    0.42
     Kitts
    0.42
     vélo
    0.41
     újra
    0.41
     hashes
    0.40
     etanol
    0.40
    滢
    0.40
     Chatur
    0.40
    Activations Density 0.001%

    No Known Activations