© 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. 195774
    Prev
    Next
    INDEX
    Explanations

    other person

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

    Redesigns and models

    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
     даже
    0.48
     Chill
    0.46
     Shield
    0.46
     even
    0.44
     Metro
    0.44
     Phi
    0.43
    哪怕
    0.43
    ’
    0.42
     Summer
    0.42
     Reserve
    0.42
    POSITIVE LOGITS
     ಲಿ
    0.57
    coherent
    0.55
    Daten
    0.54
    infodisc
    0.54
     ئە
    0.53
     데이터를
    0.53
     اولمپ
    0.52
    classified
    0.51
    bentuk
    0.51
    rahmen
    0.51
    Activations Density 0.001%

    No Known Activations