© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31823
    Prev
    Next
    INDEX
    Explanations

    Please fill out

    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
    ت
    1.20
    t
    1.06
     каса
    0.89
    #
    0.88
    tional
    0.86
    dfrac
    0.84
    Initialize
    0.83
    topic
    0.83
    zelfde
    0.81
    sdk
    0.81
    POSITIVE LOGITS
     quadrilateral
    0.87
     bilayers
    0.84
     setItems
    0.82
     shap
    0.81
     Dí
    0.78
     epitome
    0.78
     problemat
    0.77
    荔
    0.77
    յ
    0.77
     тү
    0.77
    Activations Density 0.000%

    No Known Activations