© 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. 186592
    Prev
    Next
    INDEX
    Explanations

    case study

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

    potential argument, current assets

    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
    جن
    0.51
    ه
    0.50
    وما
    0.49
    const
    0.48
    states
    0.47
    文章
    0.47
    秋
    0.46
    وبر
    0.45
    November
    0.44
    而
    0.43
    POSITIVE LOGITS
    0.51
    itto
    0.47
     kit
    0.47
     チャ
    0.46
     є
    0.46
     Ner
    0.46
     कल
    0.46
    ът
    0.46
     рок
    0.46
     предложение
    0.46
    Activations Density 0.001%

    No Known Activations