© 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. 10374
    Prev
    Next
    INDEX
    Explanations

    must be a specific type

    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
    ان
    1.41
    n
    1.37
    ৩৪
    1.25
    ৪৭
    1.21
    ها
    1.19
    k
    1.18
    kira
    1.16
    ﻒ
    1.15
    る
    1.09
    ित
    1.08
    POSITIVE LOGITS
     prokary
    1.80
     unicode
    1.62
    ൮
    1.59
     IMPRO
    1.57
     DISABLED
    1.56
    ᐸ
    1.55
    <unused501>
    1.54
    ◐
    1.54
     namespaces
    1.54
     pliers
    1.54
    Activations Density 0.009%

    No Known Activations