© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11978
    Prev
    Next
    INDEX
    Explanations

    presentation titles and song titles

    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
     called
    0.77
     exercising
    0.77
    ீ
    0.75
    :])
    0.74
     exercise
    0.72
    :</
    0.72
    :]
    0.72
    called
    0.72
    :}
    0.71
     Exercise
    0.66
    POSITIVE LOGITS
     matériau
    0.94
     Diameter
    0.93
     diamètre
    0.91
    Diameter
    0.90
     Fecha
    0.89
     मटेरियल
    0.89
     площадь
    0.86
     длиной
    0.86
     материалов
    0.86
     diameter
    0.86
    Activations Density 0.090%

    No Known Activations