© 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. 11486
    Prev
    Next
    INDEX
    Explanations

    the act of going

    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
    通り
    0.68
     transient
    0.62
    逸
    0.61
    नेटिक
    0.60
    통
    0.60
    သာ
    0.60
    বত
    0.60
    mod
    0.60
     গির
    0.59
     travers
    0.59
    POSITIVE LOGITS
     이날
    0.92
    埥
    0.90
     συγκεκρι
    0.89
    පු
    0.86
     wenn
    0.84
    ινε
    0.83
     χωρίς
    0.82
    tono
    0.81
     because
    0.81
     WITH
    0.81
    Activations Density 0.016%

    No Known Activations