© 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. 84824
    Prev
    Next
    INDEX
    Explanations

    mother would, than usual, how we

    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
    깼
    0.46
    RowFilter
    0.45
    =’
    0.45
     condado
    0.45
     crumpled
    0.44
    ahun
    0.44
     প্রথমে
    0.44
     crumbled
    0.44
     ابتدا
    0.44
     pecans
    0.44
    POSITIVE LOGITS
    Council
    0.44
    ో
    0.38
    global
    0.38
     Pash
    0.37
     गर्व
    0.36
     forecast
    0.36
    Cell
    0.36
    ้ม
    0.35
    主力
    0.35
    W
    0.35
    Activations Density 0.002%

    No Known Activations