© 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. 204303
    Prev
    Next
    INDEX
    Explanations

    discourse markers and conjunctions

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

    messaging app WeChat

    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
     taglio
    0.52
    ോദ
    0.51
     katta
    0.45
    ';"/>
    0.44
     fantastical
    0.44
     plek
    0.44
     esque
    0.44
     entonces
    0.44
     Kurds
    0.43
     alot
    0.43
    POSITIVE LOGITS
     evaluation
    0.41
    <0xE3>
    0.38
    METHODS
    0.37
    AudioManager
    0.37
    CIT
    0.36
    PushMatrix
    0.36
     الابتدائي
    0.36
     হেম
    0.36
     contentService
    0.35
    synthetic
    0.35
    Activations Density 0.000%

    No Known Activations