© 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. 6277
    Prev
    Next
    INDEX
    Explanations

    wiki after /

    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
     veines
    0.37
    vene
    0.36
    omeness
    0.36
     கரைய
    0.35
    𒉌
    0.35
    رد
    0.35
    iousness
    0.35
    maan
    0.34
     interstices
    0.34
    няется
    0.34
    POSITIVE LOGITS
    wiki
    0.55
    /%
    0.42
     wiki
    0.38
     Wiki
    0.38
     $/
    0.36
    +/
    0.35
     Special
    0.35
    w
    0.35
    zh
    0.35
     вики
    0.34
    Activations Density 0.009%

    No Known Activations