© 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-16K
    7. 1522
    Prev
    Next
    INDEX
    Explanations

    Acceptance criteria

    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_16k_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
    य
    3.16
    ส์
    3.06
     métallique
    2.70
    cerr
    2.69
    му
    2.65
     виде
    2.58
    tedy
    2.58
    mais
    2.56
    για
    2.56
    нача
    2.53
    POSITIVE LOGITS
    ना
    3.09
    नाची
    2.92
    जनक
    2.75
     acclaim
    2.71
    ٬
    2.68
     crumb
    2.64
    assertInstanceOf
    2.58
    isLoading
    2.50
    স্বর
    2.46
    فته
    2.40
    Activations Density 0.650%

    No Known Activations