© 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. 171932
    Prev
    Next
    INDEX
    Explanations

    following service or rights

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

    what each part

    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
    Negative Logits
    ~
    0.55
     in
    0.52
    ″
    0.49
     merger
    0.47
     ~
    0.46
     copy
    0.45
     DER
    0.44
    "),
    0.44
     &
    0.44
     ·
    0.44
    POSITIVE LOGITS
    జీ
    0.52
    rolo
    0.52
    㭚
    0.50
    顓
    0.50
    గి
    0.50
    Ე
    0.50
    体操
    0.50
    뇰
    0.49
    বি
    0.49
     केवल
    0.49
    Activations Density 0.000%

    No Known Activations