© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11392
    Prev
    Next
    INDEX
    Explanations

    lighthearted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ما
    2.75
    ל
    2.66
    на
    2.48
    ان
    2.47
    ات
    2.44
    כ
    2.28
    ре
    2.19
    其他
    2.09
    ש
    2.08
    ز
    2.05
    POSITIVE LOGITS
    hearted
    2.25
     indépendant
    2.02
     অন্যদিকে
    1.86
     noire
    1.84
    it
    1.79
     maven
    1.77
     gemacht
    1.74
    ab
    1.73
    سلام
    1.70
     kepada
    1.70
    Activations Density 0.044%

    No Known Activations