© 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. 16-GEMMASCOPE-2-RES-262K
    7. 139565
    Prev
    Next
    INDEX
    Explanations

    glutathione peroxidase

    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_16_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
     ఇం
    0.49
    ronique
    0.49
     atmosph
    0.45
    entions
    0.45
     surprises
    0.45
     ءِ
    0.44
     آ
    0.44
     unbear
    0.44
    ആര്‍
    0.44
    绩效
    0.43
    POSITIVE LOGITS
    目の
    0.70
     }.
    0.56
    ิน
    0.52
    ir
    0.52
    ীন
    0.52
    giraffe
    0.51
     Пример
    0.50
    ิ
    0.50
    ิท
    0.50
    ra
    0.49
    Activations Density 0.000%

    No Known Activations