© 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. 41913
    Prev
    Next
    INDEX
    Explanations

    press, misses, coder, inquiry

    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
    ב
    0.74
    м
    0.72
    ت
    0.69
    t
    0.68
    ту
    0.67
    म
    0.67
     papeles
    0.67
    ຜະລິດຕະພັນ
    0.61
    ל
    0.61
    assets
    0.59
    POSITIVE LOGITS
    od
    0.54
     ،
    0.54
    ereo
    0.52
    ⛎
    0.52
     PRP
    0.51
     إنه
    0.51
     很
    0.51
     లే
    0.50
     فور
    0.50
     اللغة
    0.50
    Activations Density 0.000%

    No Known Activations