© 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. 74173
    Prev
    Next
    INDEX
    Explanations

    send over

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

    ChatGPT

    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
    must
    0.54
    정
    0.48
    ﾁ
    0.48
    herald
    0.46
     _
    0.45
     {
    0.45
    el
    0.44
     installments
    0.44
    HEL
    0.43
    is
    0.43
    POSITIVE LOGITS
     Bianchi
    0.46
    alaikums
    0.46
    LoginActivity
    0.46
    景象
    0.44
    FileInputExcel
    0.44
    ഗീയ
    0.44
     formerly
    0.43
    尟
    0.42
    ಚ್
    0.42
    കരണ
    0.42
    Activations Density 0.000%

    No Known Activations