© 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. 107320
    Prev
    Next
    INDEX
    Explanations

    analysis of details

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

    sketching, commentary, and reliability

    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
    mentation
    0.51
    지만
    0.48
     -
    0.48
     真
    0.47
    ITAR
    0.46
    ні
    0.46
    Revelation
    0.46
    Ӏ
    0.46
    length
    0.45
    頁
    0.44
    POSITIVE LOGITS
     consiglio
    0.51
    鶉
    0.49
     raffin
    0.49
     Coun
    0.47
     analisi
    0.47
     ruso
    0.46
     speedboat
    0.46
    的海
    0.45
     planejamento
    0.45
     काउंसिल
    0.45
    Activations Density 0.001%

    No Known Activations