© 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. 175234
    Prev
    Next
    INDEX
    Explanations

    LORD his, destroy him

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

    p.y / python / microsoft / kinds of

    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
    ība
    0.49
     Ashe
    0.46
     अश्विन
    0.46
     아버지
    0.45
    áneas
    0.45
    ūt
    0.45
     흐
    0.45
    siswa
    0.45
    seeds
    0.44
    úcar
    0.43
    POSITIVE LOGITS
    ’
    0.48
    LB
    0.46
     riesce
    0.44
     interprets
    0.43
    Instagram
    0.43
    這個
    0.43
    আন্তর্জাতিক
    0.43
     toasted
    0.42
    ることができます
    0.42
    初めて
    0.41
    Activations Density 0.002%

    No Known Activations