© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 3113
    Prev
    Next
    INDEX
    Explanations

    people and their associated actions

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .”
    0.16
    。”
    0.15
     Contains
    0.15
    ?.
    0.15
     decomposition
    0.15
    .}
    0.14
                
    0.14
     Charging
    0.14
    ."
    0.14
    ().
    0.14
    POSITIVE LOGITS
     have
    0.21
     recognize
    0.18
     spend
    0.17
     perceive
    0.17
     spends
    0.16
    들은
    0.16
    たちは
    0.16
     engage
    0.16
     would
    0.15
    们
    0.15
    Activations Density 0.167%

    No Known Activations