© 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. 177137
    Prev
    Next
    INDEX
    Explanations

    adverb or following a coordinating conjunction

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

    limit potential

    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
    t
    0.57
    y
    0.54
    in
    0.52
    es
    0.52
    p
    0.50
    h
    0.50
     whopping
    0.47
     tbsp
    0.47
    et
    0.47
    il
    0.47
    POSITIVE LOGITS
    TrackAngle
    0.53
    崞
    0.52
    を中心
    0.47
    盛り
    0.46
     صحی
    0.45
     famílias
    0.45
     हिल
    0.44
     Hòa
    0.44
    िरपेक्ष
    0.44
    閑
    0.43
    Activations Density 0.000%

    No Known Activations