© 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. 95082
    Prev
    Next
    INDEX
    Explanations

    local context followed by description

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

    technical terms and concepts

    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
    2
    0.48
     james
    0.48
    。
    0.47
    ва
    0.45
    <unused61>
    0.44
     sorted
    0.43
     اكت
    0.43
    4
    0.43
     какая
    0.42
     каталог
    0.42
    POSITIVE LOGITS
     dehuman
    0.54
     Düsseldorf
    0.50
     서울
    0.48
     हान
    0.47
     Wahrheit
    0.47
    ဦး
    0.46
     Gothenburg
    0.46
    eggi
    0.45
     வெப்ப
    0.45
    ইস
    0.45
    Activations Density 0.001%

    No Known Activations