© 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. 9928
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas or colons

    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
    त
    1.78
    in
    1.27
    ず
    1.22
    रेक्ट
    1.20
    ৪২
    1.18
    סים
    1.14
    Picker
    1.14
    Haupt
    1.13
     Wunder
    1.12
     Expr
    1.12
    POSITIVE LOGITS
     мин
    1.18
     accordance
    1.10
     aún
    1.06
    ඛ
    1.04
     фараз
    1.02
     урав
    1.01
     изменений
    1.01
    ("["
    1.01
     انکار
    1.00
     개
    1.00
    Activations Density 0.000%

    No Known Activations