© 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. 59578
    Prev
    Next
    INDEX
    Explanations

    common collocations and phrases

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

    legal format, progress delay

    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
    ща
    0.50
    ﻧ
    0.45
     זאת
    0.44
    論文
    0.44
    騰
    0.44
    比べて
    0.43
    椒
    0.43
    ი
    0.43
     manipulated
    0.43
    あと
    0.43
    POSITIVE LOGITS
     हॉल
    0.56
     आँ
    0.45
    beer
    0.42
     बेटा
    0.42
    estones
    0.42
    ेडियम
    0.42
     उदाहरण
    0.41
     쉽게
    0.41
     of
    0.41
     caster
    0.40
    Activations Density 0.000%

    No Known Activations