© 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. 34352
    Prev
    Next
    INDEX
    Explanations

    communication and speech

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

    communication and language

    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
    鍬
    0.52
    フィール
    0.49
    RESOURCE
    0.48
    シーズン
    0.48
     автомо
    0.47
    特集
    0.47
     खेळा
    0.47
    錨
    0.47
    AGRIC
    0.46
    잿
    0.46
    POSITIVE LOGITS
     Communication
    1.60
     communication
    1.57
    Communication
    1.45
     comunicación
    1.43
     Language
    1.41
     comunicazione
    1.41
     comunicação
    1.39
     कम्युनिकेशन
    1.39
     Speech
    1.38
     komunik
    1.37
    Activations Density 0.144%

    No Known Activations