© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3301
    Prev
    Next
    INDEX
    Explanations

    the followed by descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    ل
    0.75
    te
    0.61
    و
    0.61
    ే
    0.57
    ↵
    0.54
    ре
    0.54
    ку
    0.53
    le
    0.49
    ри
    0.48
    وم
    0.48
    POSITIVE LOGITS
    0.66
    {
    0.57
     to
    0.57
     {
    0.52
     at
    0.52
     fiercely
    0.49
     }^{
    0.48
     of
    0.48
     która
    0.44
     flamboyant
    0.44
    Activations Density 0.256%

    No Known Activations