© 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. 10585
    Prev
    Next
    INDEX
    Explanations

    software versions or later

    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
     wayside
    1.61
    它是
    1.55
    ি
    1.49
     fester
    1.48
     mula
    1.46
     radioactivity
    1.45
    mic
    1.44
    ESTIC
    1.43
    iences
    1.42
     בו
    1.41
    POSITIVE LOGITS
    기
    1.91
    ности
    1.85
    기를
    1.50
    를
    1.46
    у
    1.43
    লি
    1.43
    ри
    1.41
     ADN
    1.40
    기에
    1.39
    기가
    1.36
    Activations Density 0.004%

    No Known Activations