© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 39178
    Prev
    Next
    INDEX
    Explanations

    hunting Orc categories

    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
    n
    0.93
    IN
    0.81
    c
    0.79
    нку
    0.78
    け
    0.78
    どう
    0.77
    म
    0.77
    ce
    0.75
    з
    0.73
    ないと
    0.71
    POSITIVE LOGITS
     dinosaurs
    1.00
     croissants
    0.99
     bathrooms
    0.96
     catheters
    0.96
     booths
    0.96
     Αγ
    0.93
     हारे
    0.93
     knots
    0.92
     oscillators
    0.92
     Couleur
    0.92
    Activations Density 0.000%

    No Known Activations