© 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. 21350
    Prev
    Next
    INDEX
    Explanations

    **Type**: Royal Bedrooms

    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
     calculations
    0.38
    Clr
    0.38
    *%
    0.37
     integrals
    0.36
    щён
    0.35
    লাগ
    0.35
    HairColor
    0.34
     solution
    0.34
    🇿
    0.34
    ->_
    0.34
    POSITIVE LOGITS
     Offer
    0.37
    mité
    0.36
    share
    0.36
     Share
    0.36
    Help
    0.36
    js
    0.36
    groupBy
    0.36
    sortBy
    0.35
     निजी
    0.35
    sandbox
    0.35
    Activations Density 0.000%

    No Known Activations