© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9123
    Prev
    Next
    INDEX
    Explanations

    conditional logic or exceptions

    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
    я
    2.06
    पत
    1.79
    ্যাক
    1.77
    ния
    1.76
    ueur
    1.74
    ї
    1.69
    ্যা
    1.69
    ỏng
    1.69
    சூ
    1.62
    諫
    1.60
    POSITIVE LOGITS
    er
    2.01
    р
    1.89
    ر
    1.86
    र
    1.83
    り
    1.81
    א
    1.66
    Р
    1.55
    い
    1.53
     elaboración
    1.50
     faktisk
    1.48
    Activations Density 0.000%

    No Known Activations