© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4955
    Prev
    Next
    INDEX
    Explanations

    describing emotional voice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Kongo
    1.21
    ilder
    1.19
    '
    1.15
    ït
    1.14
     ليب
    1.14
    стов
    1.13
    '}).
    1.12
    ld
    1.11
    __).
    1.09
     Ответ
    1.09
    POSITIVE LOGITS
     blanch
    1.14
    AGUE
    1.05
     cramping
    0.99
    phalodes
    0.99
     Ashram
    0.96
    FontStyle
    0.96
    LONDON
    0.95
    umbles
    0.94
     PARIS
    0.93
    vai
    0.93
    Activations Density 0.040%

    No Known Activations