© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9834
    Prev
    Next
    INDEX
    Explanations

    content of

    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
     impeding
    0.98
     interdit
    0.91
     marred
    0.88
     Besonders
    0.84
    ލ
    0.83
     parked
    0.82
     guessed
    0.82
     parted
    0.82
     Chances
    0.81
     ומ
    0.80
    POSITIVE LOGITS
    ek
    1.03
    een
    1.00
    ت
    1.00
    ię
    0.97
    دت
    0.96
    го
    0.96
    direccion
    0.94
    ća
    0.94
     tieto
    0.94
    de
    0.93
    Activations Density 0.004%

    No Known Activations