© 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. 11767
    Prev
    Next
    INDEX
    Explanations

    financial terms

    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
    لل
    1.31
    ت
    1.18
    Анд
    1.16
    নির্
    1.14
    т
    1.13
    rj
    1.13
    nang
    1.11
    יים
    1.11
    𝐽
    1.11
    tub
    1.08
    POSITIVE LOGITS
     italiano
    1.47
     grep
    1.38
     प्रीपेड
    1.34
     चौपट
    1.29
     Flug
    1.24
     américain
    1.21
     immune
    1.21
    욱
    1.21
    elés
    1.20
     geen
    1.20
    Activations Density 0.000%

    No Known Activations