© 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. 161734
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

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

    categorizing and defining aspects

    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
    Ｎ
    0.48
    ก
    0.48
     repug
    0.47
    inflate
    0.47
    ATTACH
    0.46
    HON
    0.45
    VAN
    0.45
    PAY
    0.45
    FLOW
    0.45
    Н
    0.45
    POSITIVE LOGITS
    izabeth
    0.49
     outcrops
    0.48
     disponibles
    0.47
    neider
    0.46
     大阪
    0.46
     เด่น
    0.46
     संदेश
    0.45
     richesse
    0.45
     classement
    0.45
     Vậy
    0.45
    Activations Density 0.000%

    No Known Activations