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. 8314
    Prev
    Next
    INDEX
    Explanations

    hands reaching for things

    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
    т
    1.23
    ્સ
    1.17
    ST
    1.16
    GAL
    1.13
    GHz
    1.12
    LER
    1.09
    MDA
    1.09
    R
    1.02
    broke
    1.01
    KIS
    1.00
    POSITIVE LOGITS
     pouze
    1.33
    নাই
    1.27
    க்கு
    1.26
     ít
    1.24
    aný
    1.24
    له
    1.23
     ideals
    1.23
     мире
    1.23
     arī
    1.23
     הראשון
    1.22
    Activations Density 0.003%

    No Known Activations