© 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. 23507
    Prev
    Next
    INDEX
    Explanations

    number and scientific terms

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

    ask it

    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
    Tổng
    0.48
    騫
    0.47
     свер
    0.44
    Million
    0.44
    เชิง
    0.44
    קו
    0.43
    शासन
    0.43
    Ongoing
    0.43
    穆
    0.42
    ục
    0.42
    POSITIVE LOGITS
     valam
    0.44
     nee
    0.42
    某种
    0.39
     manifi
    0.39
     Huntingdon
    0.39
     AMPK
    0.38
     discíp
    0.38
     algún
    0.37
     maternity
    0.37
     reactance
    0.37
    Activations Density 0.000%

    No Known Activations