© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71437
    Prev
    Next
    INDEX
    Explanations

    common tokens followed by conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ag
    0.49
    erenza
    0.47
    Iy
    0.46
    őség
    0.46
    CommonAncestor
    0.45
    r
    0.44
     умира
    0.44
     ему
    0.43
     übrigens
    0.43
    曦
    0.42
    POSITIVE LOGITS
    وت
    0.52
    قد
    0.45
    س
    0.45
    clicking
    0.45
    مت
    0.43
     everything
    0.43
    tapping
    0.43
    껌
    0.42
    everything
    0.41
     freestanding
    0.41
    Activations Density 0.001%

    No Known Activations