© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22657
    Prev
    Next
    INDEX
    Explanations

    human-quality text

    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
    樎
    0.39
     keySchedule
    0.38
    泬
    0.37
    ्वेस्ट
    0.36
    ەش
    0.36
     hipster
    0.35
     oeuvre
    0.35
    ریشن
    0.34
     menyer
    0.34
     malzeme
    0.33
    POSITIVE LOGITS
    -
    0.65
    _
    0.44
    −
    0.41
    ‐
    0.39
    (-
    0.37
    –
    0.34
     অর্থাৎ
    0.33
    ‌
    0.33
    and
    0.32
    ‒
    0.32
    Activations Density 0.033%

    No Known Activations