© 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. 30971
    Prev
    Next
    INDEX
    Explanations

    square meters, browser view, football match, cycles GmbH

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

    smooth transition effect

    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
    Responsibilities
    0.52
    Jeśli
    0.47
    În
    0.44
    こんにちは
    0.44
    ખ
    0.44
    sitting
    0.44
    pli
    0.44
    Ils
    0.43
    इसके
    0.43
    Increase
    0.43
    POSITIVE LOGITS
     v
    0.50
     mackerel
    0.50
     hundred
    0.49
     Native
    0.49
     V
    0.48
     Hundred
    0.47
     harm
    0.47
     Xamarin
    0.46
     predicate
    0.45
     ICO
    0.45
    Activations Density 0.001%

    No Known Activations