© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191792
    Prev
    Next
    INDEX
    Explanations

    listing verbs and places

    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_40_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
    紘
    0.43
    kadot
    0.38
    γρά
    0.38
    કરી
    0.37
    বয়
    0.36
    etva
    0.36
    සර
    0.36
    모델
    0.36
    సో
    0.35
    nath
    0.35
    POSITIVE LOGITS
     neglected
    0.46
    omac
    0.42
     quantitative
    0.42
    <0x19>
    0.42
    зде
    0.42
     கூடு
    0.42
    leps
    0.41
     tyr
    0.41
     ottimo
    0.40
     aq
    0.40
    Activations Density 0.000%

    No Known Activations