© 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. 224143
    Prev
    Next
    INDEX
    Explanations

    common grammatical phrases

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

    muscle contraction, control, or reporting

    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
     rigid
    0.43
     anthracite
    0.42
     arah
    0.41
    args
    0.40
     sensibility
    0.39
     directional
    0.39
     structured
    0.38
    ८
    0.38
     $(*
    0.37
     molasses
    0.37
    POSITIVE LOGITS
     potuto
    0.54
     tiden
    0.52
    就能
    0.48
     পাবেন
    0.47
    䢍
    0.46
    ပြော
    0.46
     podían
    0.46
     你
    0.45
     podía
    0.45
     отрима
    0.45
    Activations Density 0.000%

    No Known Activations