© 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. 42167
    Prev
    Next
    INDEX
    Explanations

    clear history, cache, screen

    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
    。
    2.00
    یت
    1.91
    こと
    1.90
    ときは
    1.84
    ం
    1.82
    ки
    1.80
    ம்
    1.71
    とき
    1.66
     endeav
    1.66
    ،
    1.66
    POSITIVE LOGITS
    DES
    2.08
    er
    2.06
    DOM
    1.95
    NING
    1.94
    DIS
    1.91
    TH
    1.91
     posséd
    1.89
    ר
    1.76
    erne
    1.71
    DR
    1.69
    Activations Density 0.015%

    No Known Activations