© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130886
    Prev
    Next
    INDEX
    Explanations

    good for supplementing

    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
     arbitrarily
    0.41
    órc
    0.38
    ர்வ
    0.37
    هران
    0.37
    󠁬
    0.37
    ному
    0.36
    ţiile
    0.36
    下一个
    0.35
    ěl
    0.35
    蹟
    0.34
    POSITIVE LOGITS
     supplement
    2.80
     supplementing
    2.63
     complement
    2.55
    supplement
    2.55
     supplemental
    2.53
     supplementary
    2.52
     supplemented
    2.45
     complementing
    2.41
     Supplement
    2.38
     допол
    2.38
    Activations Density 0.147%

    No Known Activations