© 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. 37047
    Prev
    Next
    INDEX
    Explanations

    sequences indicating quantity or condition

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

    material or application details

    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
    Sounds
    0.54
    ту
    0.52
    ലോക
    0.51
    UT
    0.50
    삼성
    0.50
    麹
    0.49
    ग
    0.49
    Этот
    0.48
    Га
    0.48
     عملية
    0.47
    POSITIVE LOGITS
    <0x8F>
    0.50
    <0x91>
    0.49
    enchymal
    0.47
    unnel
    0.46
     murid
    0.45
     apparten
    0.45
     empath
    0.45
    ym
    0.44
    eni
    0.43
    ىڭ
    0.43
    Activations Density 0.001%

    No Known Activations