© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9872
    Prev
    Next
    INDEX
    Explanations

    proper names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ر
    2.17
    waves
    1.81
    ra
    1.69
    time
    1.63
    r
    1.55
    ર
    1.54
    ্যা
    1.53
    tones
    1.52
    ri
    1.50
    ר
    1.45
    POSITIVE LOGITS
    ﻥ
    1.59
     значительно
    1.46
    पणा
    1.44
    তরাং
    1.43
    തിരെ
    1.39
    এবং
    1.39
    ഭ്യാസ
    1.38
    Formerly
    1.37
    க்கழக
    1.37
    দেখে
    1.37
    Activations Density 0.028%

    No Known Activations