© 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. 31-GEMMASCOPE-2-RES-262K
    7. 143810
    Prev
    Next
    INDEX
    Explanations

    down into keyphrases

    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_31_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
    liğini
    0.49
    шить
    0.49
    翟
    0.49
    羢
    0.49
    сування
    0.47
    كس
    0.47
    भारत
    0.47
    राय
    0.47
    اگر
    0.45
    Якщо
    0.45
    POSITIVE LOGITS
     folks
    0.60
     C
    0.57
     but
    0.53
     Restaurant
    0.52
     R
    0.51
     “
    0.50
     jQuery
    0.50
     Microsoft
    0.49
     spell
    0.48
     ”
    0.48
    Activations Density 0.005%

    No Known Activations