© 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. 216203
    Prev
    Next
    INDEX
    Explanations

    household items and tools

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

    your domain

    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
    rdquo
    0.47
    भीर
    0.47
    ៤
    0.47
    ழ
    0.46
    ści
    0.46
     фер
    0.46
    Recorder
    0.46
    rowad
    0.46
    ringer
    0.45
    }^{(
    0.45
    POSITIVE LOGITS
     payloads
    0.54
     Wallet
    0.50
     Painting
    0.46
     Na
    0.46
     economies
    0.46
     cloison
    0.45
     Klo
    0.44
     endpoints
    0.44
     electroweak
    0.44
     unitarity
    0.44
    Activations Density 0.000%

    No Known Activations