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. 3907
    Prev
    Next
    INDEX
    Explanations

    export default statements

    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
    ка
    2.05
    ні
    2.05
    ен
    1.70
    إذا
    1.70
    TEMPERATURE
    1.63
    ن
    1.61
    ENGINE
    1.60
    THREADS
    1.59
    τά
    1.59
    ران
    1.57
    POSITIVE LOGITS
     Dile
    1.51
     harden
    1.41
    ge
    1.40
    chie
    1.39
     afar
    1.31
     angeboten
    1.28
     Dif
    1.27
     Ceiling
    1.25
     aberrations
    1.24
     (
    1.23
    Activations Density 0.002%

    No Known Activations