© 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. 9890
    Prev
    Next
    INDEX
    Explanations

    ROI analysis

    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
     batas
    1.58
    <html>
    1.58
    годні
    1.54
    𝑈
    1.48
     deformations
    1.48
     années
    1.47
    trusive
    1.46
    知道
    1.44
    ,{\
    1.43
     amplitudes
    1.42
    POSITIVE LOGITS
    ா
    2.12
    ת
    1.82
    ী
    1.80
    ات
    1.78
    atge
    1.68
    ே
    1.65
    pecific
    1.64
    тэй
    1.61
     HINSTANCE
    1.61
    ష్ట
    1.59
    Activations Density 0.001%

    No Known Activations