Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 44682
    Prev
    Next
    INDEX
    Explanations

    mess

    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
     syg
    1.45
    ی
    1.29
     устойчи
    1.28
     gimnas
    1.23
    یه
    1.23
    お客
    1.22
     तु
    1.20
     autopsy
    1.20
     игра
    1.18
     espes
    1.17
    POSITIVE LOGITS
    lng
    1.08
    ings
    1.03
    ures
    1.03
    ör
    1.02
    ier
    1.02
    ер
    1.01
    i
    0.98
    olds
    0.98
    aged
    0.97
    oval
    0.97
    Activations Density 0.000%

    No Known Activations