© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 20203
    Prev
    Next
    INDEX
    Explanations

    I want to go see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     an
    0.47
     a
    0.46
     (
    0.46
    El
    0.45
     direccion
    0.45
    ім
    0.45
    ウム
    0.44
     telles
    0.44
     algún
    0.44
    ری
    0.44
    POSITIVE LOGITS
    憉
    0.47
    perature
    0.45
     சேர்த்து
    0.44
    षेक
    0.44
     októ
    0.43
    তলা
    0.42
    дня
    0.42
    謃
    0.42
    求解
    0.41
    匙
    0.41
    Activations Density 0.001%

    No Known Activations