© 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. 6873
    Prev
    Next
    INDEX
    Explanations

    wifi connection

    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
    ד
    2.17
    Н
    1.82
    ហ៊ុន
    1.80
    THING
    1.79
    dı
    1.78
    İN
    1.78
    يت
    1.74
    tól
    1.68
    ০
    1.68
    encia
    1.64
    POSITIVE LOGITS
    ้ง
    1.78
    琲
    1.65
     dizzy
    1.63
     pullover
    1.62
     touchscreen
    1.61
     blinding
    1.48
     vengeance
    1.45
     magnetism
    1.45
     caustic
    1.45
     breathing
    1.43
    Activations Density 0.015%

    No Known Activations