© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 11936
    Prev
    Next
    INDEX
    Explanations

    ray tracing, Bay Area, grey/gray

    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_22_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
    ীয়
    1.64
    ില്ല
    1.34
    ियां
    1.34
    ान्त
    1.28
    ীয়
    1.22
    ार्थ
    1.22
     irony
    1.19
    a
    1.16
     té
    1.15
    িন
    1.13
    POSITIVE LOGITS
    yyyyyyyy
    2.27
    yyyy
    1.99
    ുടെ
    1.89
    ोजक
    1.88
    evich
    1.82
    yy
    1.81
    onnaise
    1.79
    untamiento
    1.79
    oung
    1.77
    ne
    1.76
    Activations Density 0.126%

    No Known Activations