© 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. 173909
    Prev
    Next
    INDEX
    Explanations

    real estate, appointments, therapy, days

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

    Search, language, network, chips, reduce

    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
    ğ
    0.49
    临
    0.48
    伤
    0.48
    难
    0.44
    び
    0.43
    ಋ
    0.43
    れる
    0.43
     நம்
    0.42
    秦
    0.41
     in
    0.41
    POSITIVE LOGITS
     durchaus
    0.52
     Penta
    0.49
     dexterity
    0.47
    ল্যান্ড
    0.45
    nections
    0.45
    osilicate
    0.44
     музыку
    0.44
     Estab
    0.44
     Lehr
    0.44
     dandelion
    0.44
    Activations Density 0.000%

    No Known Activations