© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30274
    Prev
    Next
    INDEX
    Explanations

    account 333

    np_acts-logits-general · gemini-2.5-flash-lite

    contrast and sequence indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MUCH
    0.44
    ಷ
    0.43
     histone
    0.42
    \
    0.41
    有一些
    0.41
    架
    0.39
    Vit
    0.38
     聞
    0.38
    州的
    0.38
    佂
    0.38
    POSITIVE LOGITS
    innov
    0.47
    创始
    0.45
    grandmother
    0.45
     Unilever
    0.44
    nocześnie
    0.44
    创新
    0.43
     pourtant
    0.43
    at
    0.42
    reuse
    0.42
    great
    0.41
    Activations Density 0.000%

    No Known Activations