© 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. 42561
    Prev
    Next
    INDEX
    Explanations

    achieving a milestone

    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
    ING
    2.03
    derived
    1.92
    ’
    1.91
    tenant
    1.88
    thermal
    1.85
    says
    1.84
    sided
    1.83
    divided
    1.82
    domain
    1.81
    scaling
    1.80
    POSITIVE LOGITS
    га
    2.05
    ل
    1.97
    ى
    1.76
    ك
    1.71
    ו
    1.71
    у
    1.69
    א
    1.68
    ку
    1.64
    ท์
    1.58
    ва
    1.57
    Activations Density 0.001%

    No Known Activations