© 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. 38058
    Prev
    Next
    INDEX
    Explanations

    wave pattern

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

    sending options

    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
    چھ
    0.52
    ሸ
    0.52
    Xiaomi
    0.50
    ianza
    0.45
    ிக
    0.45
    کام
    0.44
     manifi
    0.43
     merciless
    0.43
    ן
    0.43
     компен
    0.43
    POSITIVE LOGITS
    recen
    0.52
    ifices
    0.50
    orderInCategory
    0.49
    ATIONS
    0.48
    pective
    0.47
     ura
    0.47
    LookAndFeelInfo
    0.47
    ULATIONS
    0.46
    '
    0.46
    rak
    0.45
    Activations Density 0.000%

    No Known Activations