© 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. 153882
    Prev
    Next
    INDEX
    Explanations

    you before

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

    constructs, arguments, and conditions

    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
    Handles
    0.44
    Hen
    0.42
     Workforce
    0.42
     Paddy
    0.40
    素晴らしい
    0.40
     valuation
    0.40
     Guided
    0.40
    ]}{\
    0.40
     payroll
    0.39
    ্সর
    0.39
    POSITIVE LOGITS
     anderem
    0.54
    自体
    0.53
    h
    0.53
    ups
    0.52
    w
    0.52
    を確認
    0.50
    купно
    0.50
    लामा
    0.50
     זאת
    0.50
    ing
    0.49
    Activations Density 0.001%

    No Known Activations