© 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. 68622
    Prev
    Next
    INDEX
    Explanations

    earnings reports

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

    product vision

    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
     ပါ
    0.53
     prawdopod
    0.52
    ጵ
    0.52
     tighter
    0.51
     filamentous
    0.51
     ventricular
    0.50
     ကို
    0.50
     propel
    0.50
     polyphen
    0.49
     criss
    0.49
    POSITIVE LOGITS
    arran
    0.49
    ARR
    0.47
    bu
    0.46
    С
    0.45
    Danh
    0.45
    canal
    0.45
    D
    0.45
    CYCLE
    0.44
    CHAR
    0.44
    cht
    0.43
    Activations Density 0.000%

    No Known Activations