© 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. 403
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    YLE
    0.38
     at
    0.36
    ETS
    0.33
    。）
    0.33
    ERT
    0.32
    。
    0.32
     to
    0.32
    ’).
    0.31
    NER
    0.31
    раль
    0.30
    POSITIVE LOGITS
    و
    0.50
    u
    0.47
    ת
    0.44
    us
    0.44
    <0x80>
    0.42
    os
    0.34
    as
    0.33
    にっいて
    0.33
    ა
    0.33
    ו
    0.33
    Activations Density 0.279%

    No Known Activations