© 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. 135241
    Prev
    Next
    INDEX
    Explanations

    Medical and technical procedures

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

    health, pipeline, affect

    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
    als
    0.53
    sp
    0.47
    }",
    0.47
    सिटी
    0.46
     hiçbir
    0.46
     taim
    0.45
    yim
    0.45
    /",
    0.44
    :”
    0.44
    set
    0.44
    POSITIVE LOGITS
    цата
    0.54
     రుణ
    0.53
     Weise
    0.53
    чені
    0.52
     దీని
    0.48
    意義
    0.47
     Пусть
    0.47
     Wenn
    0.45
    чната
    0.45
     విలువ
    0.44
    Activations Density 0.000%

    No Known Activations