© 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. 139302
    Prev
    Next
    INDEX
    Explanations

    flu, H3N2, genes

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

    Abuse Signs

    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
    VECTOR
    0.50
    ۔
    0.48
    hydrocèle
    0.46
    amek
    0.46
    メータ
    0.46
    INER
    0.46
    criterion
    0.45
    CIRCLE
    0.45
    ARTICLE
    0.45
     ಹೃದಯ
    0.45
    POSITIVE LOGITS
     bread
    0.48
     of
    0.47
     job
    0.47
     rung
    0.45
    颜值
    0.44
     riffs
    0.43
    烘
    0.43
    4
    0.42
    icult
    0.42
    3
    0.41
    Activations Density 0.001%

    No Known Activations