© 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. 172336
    Prev
    Next
    INDEX
    Explanations

    freeway, front, heavy, ethanol, wood

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

    features and balanced systems

    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
    წყ
    0.60
    x
    0.51
    ნ
    0.50
    რ
    0.50
     consult
    0.49
    footnote
    0.49
    wiz
    0.49
    াদেশিক
    0.49
    PW
    0.48
    р
    0.48
    POSITIVE LOGITS
     काटे
    0.52
     Rami
    0.49
    :=\
    0.48
    Emojis
    0.48
    Variables
    0.47
     abusing
    0.47
    Algebra
    0.46
     सह
    0.46
     Hager
    0.46
    '
    0.46
    Activations Density 0.000%

    No Known Activations