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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 38242
    Prev
    Next
    INDEX
    Explanations

    thrive

    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
    ak
    2.41
    ك
    2.30
    ма
    2.00
    f
    1.91
    ור
    1.89
    ہ
    1.84
    ู
    1.84
    ITIVE
    1.80
    ं
    1.78
    í
    1.78
    POSITIVE LOGITS
    يد
    1.99
    aft
    1.66
    lite
    1.58
    Vet
    1.48
    کاری
    1.41
     Vorteil
    1.41
    િજા
    1.40
    Vida
    1.40
     raged
    1.39
    ać
    1.38
    Activations Density 0.003%

    No Known Activations