© 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. 84262
    Prev
    Next
    INDEX
    Explanations

    adverbs followed by complements

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

    explaining AI limitations and opinions

    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
    SEASON
    0.46
    （
    0.46
     BEAR
    0.43
     非
    0.42
    жде
    0.41
    ではない
    0.41
    ノン
    0.40
    悟
    0.40
    <h1>
    0.40
    非
    0.40
    POSITIVE LOGITS
     Lukas
    0.45
     videoj
    0.44
    utilizzo
    0.44
     legado
    0.43
     óleo
    0.43
    犸
    0.42
     iban
    0.42
    鋃
    0.42
     broadcaster
    0.41
     itd
    0.41
    Activations Density 0.001%

    No Known Activations