© 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. 35859
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    لوں
    1.00
    ی
    0.91
    ה
    0.86
    䄱
    0.86
     luglio
    0.85
    an
    0.84
     około
    0.83
     ३
    0.81
    ३
    0.81
    粓
    0.81
    POSITIVE LOGITS
     programming
    0.81
     multer
    0.80
     influence
    0.74
     ergonomics
    0.73
     groundwork
    0.73
     expressive
    0.72
     forks
    0.71
     Express
    0.70
     bargaining
    0.70
     wiring
    0.69
    Activations Density 0.000%

    No Known Activations