© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47253
    Prev
    Next
    INDEX
    Explanations

    stars or modeling or unsafe

    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
     न्यूज़
    0.46
    Ꮟ
    0.46
    ますが
    0.46
    穌
    0.45
    ること
    0.44
    り
    0.43
    മ്ബ
    0.42
     apparaît
    0.42
     fanáticos
    0.42
     tatou
    0.42
    POSITIVE LOGITS
     daytime
    0.52
    an
    0.52
    croll
    0.52
    fter
    0.51
    eig
    0.51
    halla
    0.49
    a
    0.49
    e
    0.49
     weekdays
    0.48
    usic
    0.48
    Activations Density 0.001%

    No Known Activations