© 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. 18485
    Prev
    Next
    INDEX
    Explanations

    enable or provide

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

    quantification, data, technical terms

    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
    ците
    0.49
    ריק
    0.48
    Gregor
    0.47
    טי
    0.47
    צי
    0.47
     Ramesh
    0.46
    亟
    0.43
     Dewan
    0.43
     Bunker
    0.42
    ನಗೆ
    0.42
    POSITIVE LOGITS
     يا
    0.46
     followed
    0.45
     bordered
    0.42
    とした
    0.42
     furrow
    0.41
     pursued
    0.41
    骚
    0.41
     σε
    0.40
     einem
    0.39
    ˨
    0.39
    Activations Density 0.000%

    No Known Activations