© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5162
    Prev
    Next
    INDEX
    Explanations

    news sources and publications

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

    news articles

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Prothorax
    0.40
     CaCO
    0.40
     Paleo
    0.38
     ≥
    0.38
     wymaga
    0.36
     Phylogenetic
    0.36
     Oxidation
    0.36
    样品
    0.36
    颞
    0.36
     Epoxy
    0.36
    POSITIVE LOGITS
    news
    0.84
     news
    0.77
    Reuters
    0.69
     berita
    0.69
    News
    0.65
     Reuters
    0.65
     notícias
    0.65
     noticias
    0.64
     periodistas
    0.64
     journalist
    0.64
    Activations Density 0.580%

    No Known Activations