© 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. 106839
    Prev
    Next
    INDEX
    Explanations

    for specific items or purposes

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

    design, again, continuous, STRING, containing, strategy, plains

    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
     nécessairement
    0.52
    島の
    0.48
     島
    0.48
     recklessly
    0.47
     dynamically
    0.46
     வழி
    0.45
    Lopez
    0.45
     genealog
    0.45
     kontrak
    0.45
     insanların
    0.44
    POSITIVE LOGITS
    ંદર
    0.51
    敲
    0.49
    场所
    0.47
    n
    0.47
    执行
    0.47
    hnt
    0.46
    不少
    0.45
    嗨
    0.45
    ल्दी
    0.45
    两
    0.45
    Activations Density 0.000%

    No Known Activations