© 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. 123870
    Prev
    Next
    INDEX
    Explanations

    evaluating performance

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

    states of being

    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
    I
    0.63
    –
    0.52
    Travel
    0.46
     (
    0.46
    Fake
    0.45
    Technology
    0.44
     Open
    0.44
    0.44
     I
    0.44
    iali
    0.43
    POSITIVE LOGITS
     nettoyer
    0.53
    ₚ
    0.50
    fNil
    0.49
    isopropyl
    0.49
     separar
    0.49
     ölç
    0.48
     humides
    0.48
    ربع
    0.48
     партии
    0.48
     ماس
    0.48
    Activations Density 0.001%

    No Known Activations