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. 24-GEMMASCOPE-2-RES-16K
    4. 7219
    Prev
    Next
    INDEX
    Explanations

    followingsuperheroControls

    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_24_width_16k_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
     två
    0.88
     zeml
    0.80
     Ελλά
    0.78
     aşk
    0.78
    Ꭾ
    0.78
     wèi
    0.77
     dø
    0.77
     lugar
    0.76
     двух
    0.76
     данные
    0.76
    POSITIVE LOGITS
     habituellement
    0.73
    يث
    0.73
    atiquement
    0.71
     réellement
    0.71
    {}".
    0.69
     Controls
    0.69
     constituer
    0.69
     Officers
    0.68
     ataupun
    0.67
     Controllers
    0.67
    Activations Density 0.011%

    No Known Activations