© 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. 46699
    Prev
    Next
    INDEX
    Explanations

    less than or showing less

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

    reducing words to their base

    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
    科技有限公司
    0.45
    station
    0.43
    τε
    0.42
     tomography
    0.42
    道
    0.42
     io
    0.41
    in
    0.41
    at
    0.40
    sama
    0.40
    tea
    0.40
    POSITIVE LOGITS
     emphatic
    0.61
     upbeat
    0.45
     గు
    0.45
    流れ
    0.45
    ட்டம்
    0.45
     kõik
    0.44
     giddy
    0.43
     sensational
    0.43
    飜
    0.43
    วรร
    0.43
    Activations Density 0.000%

    No Known Activations