© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84399
    Prev
    Next
    INDEX
    Explanations

    step 1: eliminate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    مار
    0.47
     is
    0.46
    ش
    0.45
     expressão
    0.45
    لاست
    0.45
     inscre
    0.44
    ف
    0.44
     permintaan
    0.44
     icono
    0.44
     testimonio
    0.44
    POSITIVE LOGITS
    暨
    0.49
    ご了承
    0.48
    WindowEvent
    0.46
    addAll
    0.44
    Wage
    0.43
    ♟
    0.43
    ्यक्रम
    0.43
     Freude
    0.43
    ₿
    0.43
    <0xD4>
    0.42
    Activations Density 0.000%

    No Known Activations