© 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. 147666
    Prev
    Next
    INDEX
    Explanations

    heading levels

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

    technical and academic lexicon

    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
     grated
    0.49
     IComparable
    0.48
     Rechnung
    0.48
    ವನ್ನು
    0.46
    ট
    0.45
    िक्त
    0.43
    ীষ
    0.43
    awie
    0.42
    PhotoImage
    0.42
    ()!=
    0.42
    POSITIVE LOGITS
     sarkar
    0.53
    𝔬
    0.46
     orche
    0.44
    --’
    0.44
     devre
    0.43
    யம்
    0.42
     posse
    0.42
     negotiator
    0.42
     elenco
    0.42
     governance
    0.42
    Activations Density 0.001%

    No Known Activations