© 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. 12685
    Prev
    Next
    INDEX
    Explanations

    numbers and order

    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
    0
    0.47
    id
    0.46
    this
    0.45
    这个
    0.44
    3
    0.43
    This
    0.43
    m
    0.41
    b
    0.41
    а
    0.41
    more
    0.39
    POSITIVE LOGITS
     réellement
    0.43
    身后
    0.40
    ড়ী
    0.38
    をする
    0.38
    šky
    0.38
    ﺘ
    0.38
     dries
    0.37
     zorgt
    0.37
     nantinya
    0.37
     vídeos
    0.36
    Activations Density 0.000%

    No Known Activations