Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 13666
    Prev
    Next
    INDEX
    Explanations

    there is/are

    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
    Percentage
    0.54
    руд
    0.51
    xcuserdatad
    0.50
    łasz
    0.47
    ']);
    0.47
    цій
    0.46
    crackers
    0.46
    Ordinate
    0.45
    立つ
    0.45
    calculator
    0.45
    POSITIVE LOGITS
     slit
    0.52
    م
    0.52
     beanie
    0.51
     dugo
    0.50
     kung
    0.50
     retinal
    0.49
     für
    0.49
     kama
    0.49
     suur
    0.49
     tof
    0.49
    Activations Density 0.000%

    No Known Activations