© 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-65K
    7. 2081
    Prev
    Next
    INDEX
    Explanations

    change and evolution over time

    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_65k_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
    0.28
     an
    0.24
     you
    0.23
    ni
    0.23
     shoes
    0.23
     deducted
    0.22
     +
    0.21
     einzige
    0.21
     him
    0.21
    ak
    0.21
    POSITIVE LOGITS
     вследствие
    0.29
    하여
    0.29
     dần
    0.28
     بسبب
    0.26
     tremendously
    0.26
    ת
    0.25
    며
    0.25
    з
    0.25
    ᙱ
    0.25
    สู่
    0.25
    Activations Density 0.485%

    No Known Activations