© 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. 195800
    Prev
    Next
    INDEX
    Explanations

    discourse behavior

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

    analyzes descriptions; sounds; video

    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
     później
    0.53
     později
    0.47
    鋯
    0.46
     terrified
    0.44
     банк
    0.44
    쟈
    0.44
    嚩
    0.43
     þei
    0.43
    ică
    0.42
    ńskich
    0.42
    POSITIVE LOGITS
     a
    0.61
     discorso
    0.48
     Bezug
    0.47
    havior
    0.47
     distinguishable
    0.46
     Discourse
    0.46
    appears
    0.46
    appear
    0.44
     appears
    0.44
     Plat
    0.43
    Activations Density 0.001%

    No Known Activations