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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16140
    Prev
    Next
    INDEX
    Explanations

    qualities or characteristics

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

    nuance, flexibility, non-English characters

    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_16k_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
     тех
    0.49
     pedagogy
    0.46
     wander
    0.46
     scholarship
    0.44
    療
    0.43
     perplex
    0.43
     humanoid
    0.43
     methodology
    0.42
     governing
    0.42
     весе
    0.42
    POSITIVE LOGITS
    ０
    0.54
    ５
    0.54
    )،
    0.53
    ^
    0.52
    ්‍
    0.50
    ক
    0.50
     pią
    0.49
    ৪২
    0.49
     ouvrir
    0.49
    క్
    0.49
    Activations Density 0.621%

    No Known Activations