© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10764
    Prev
    Next
    INDEX
    Explanations

    market, rough, bumpy

    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
    തിരെ
    1.64
     radiographs
    1.45
     ofici
    1.40
     монасты
    1.34
     edo
    1.33
    ح
    1.30
     メール
    1.29
     קי
    1.28
    เอ
    1.25
    বায়
    1.25
    POSITIVE LOGITS
    𝙞
    1.29
    #[
    1.20
    𝗶
    1.16
    𝘪
    1.14
    ダウン
    1.07
     mathvariant
    1.05
    λαν
    1.04
    ρών
    1.02
    ^{
    1.01
    出典
    1.01
    Activations Density 0.000%

    No Known Activations