© 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. 131244
    Prev
    Next
    INDEX
    Explanations

    loaf of, these chamber, Judging others

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

    events and their causes

    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
    뺑
    0.48
    擅
    0.47
    تح
    0.46
    떄
    0.46
    ato
    0.44
    ﺘ
    0.44
    ິດຕ
    0.43
    porters
    0.43
    佷
    0.43
    Follow
    0.43
    POSITIVE LOGITS
     مرک
    0.49
    onesian
    0.49
     multitud
    0.46
     kater
    0.46
     wsp
    0.45
     EI
    0.45
     kilómetros
    0.44
     }{}_{\
    0.44
     yielded
    0.44
     اسی
    0.44
    Activations Density 0.000%

    No Known Activations