© 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. 80034
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and adverbs followed by specific continuations

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

    not by, or supported by

    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
    ร
    0.44
    骏
    0.44
    தார
    0.44
    הר
    0.44
     создать
    0.43
    ince
    0.43
     fools
    0.43
     माय
    0.43
    ぺ
    0.42
    ทอง
    0.42
    POSITIVE LOGITS
     davranış
    0.48
     streamed
    0.47
     engaged
    0.46
     actuators
    0.45
     പരിശീല
    0.45
     redefined
    0.44
     Schenectady
    0.44
     practiced
    0.44
     mentored
    0.44
    ফুদ্দিন
    0.44
    Activations Density 0.000%

    No Known Activations