© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164460
    Prev
    Next
    INDEX
    Explanations

    ly adverbial endings

    np_acts-logits-general · gemini-2.5-flash-lite

    explain why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tragically
    0.48
    ស្ត
    0.47
    хара
    0.47
    қы
    0.46
    за
    0.45
    嗡
    0.45
    лах
    0.44
    kách
    0.44
    iktok
    0.43
    лана
    0.43
    POSITIVE LOGITS
     Syrup
    0.53
    长
    0.47
     regelmatig
    0.46
     alignments
    0.43
    萝卜
    0.43
     overriding
    0.43
     Hooks
    0.43
    แรม
    0.43
    رسی
    0.43
     Allows
    0.42
    Activations Density 0.001%

    No Known Activations