© 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. 1143
    Prev
    Next
    INDEX
    Explanations

    verbs of knowledge and perception

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

    seeing and understanding

    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
    ังก
    0.16
    АСС
    0.15
     newline
    0.15
    ؘ
    0.14
    க்கு
    0.14
    \
    0.14
    视图
    0.14
     VIEW
    0.14
     đáo
    0.14
     对于
    0.13
    POSITIVE LOGITS
     something
    0.18
     něco
    0.17
     it
    0.17
     гораздо
    0.17
     ktoś
    0.17
    自己在
    0.17
    ა
    0.17
     them
    0.17
     people
    0.17
     iets
    0.16
    Activations Density 0.656%

    No Known Activations