© 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. 35248
    Prev
    Next
    INDEX
    Explanations

    's make the you 0 objects product m use

    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
     ਆਪਣੇ
    0.86
    м
    0.84
     प्रे
    0.79
    ｶ
    0.78
    tenberg
    0.76
    िनय
    0.75
     اللَّ
    0.75
    ਂ
    0.75
     toll
    0.74
    ۔۔
    0.73
    POSITIVE LOGITS
    Ako
    0.91
    ктора
    0.87
     guérison
    0.87
    Warnings
    0.86
    তবে
    0.84
    Health
    0.84
    嚎
    0.83
     naar
    0.82
    Services
    0.82
    HCR
    0.81
    Activations Density 0.000%

    No Known Activations