© 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. 27389
    Prev
    Next
    INDEX
    Explanations

    curvy body shapes and figures

    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
     (
    0.78
    ings
    0.68
    ts
    0.64
    ä
    0.58
    ins
    0.58
    ets
    0.57
     dien
    0.57
    å
    0.56
    ish
    0.56
    ton
    0.55
    POSITIVE LOGITS
    ക
    0.71
    罗斯
    0.62
    رک
    0.62
    POSIT
    0.61
     Itália
    0.61
     мүмк
    0.61
    ক্
    0.60
     Kā
    0.60
    Resposta
    0.60
    લમાં
    0.59
    Activations Density 0.024%

    No Known Activations