© 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. 37264
    Prev
    Next
    INDEX
    Explanations

    rumors speak / persist

    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
    鯢
    0.50
     solvable
    0.48
    azz
    0.47
     吃
    0.46
    zość
    0.46
     تحد
    0.46
    tywn
    0.45
    ቤ
    0.45
     평
    0.45
     निरा
    0.45
    POSITIVE LOGITS
    Superior
    0.47
     Superior
    0.46
     Lowest
    0.43
    which
    0.42
    Foi
    0.42
    Excellent
    0.41
    Single
    0.41
    Мо
    0.41
    Statistical
    0.41
    Τα
    0.40
    Activations Density 0.001%

    No Known Activations