© 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. 101387
    Prev
    Next
    INDEX
    Explanations

    award, beauty, dream, downtime

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

    declarative sentences

    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
    <0xE7>
    0.48
     低
    0.48
     天然
    0.47
     ભર
    0.46
     Muay
    0.46
     品質
    0.46
     Fc
    0.46
     淡
    0.45
     SHIPPING
    0.45
     Drainage
    0.45
    POSITIVE LOGITS
    말
    0.47
    emples
    0.46
    불
    0.45
    바이
    0.45
    ências
    0.45
    ภาษา
    0.45
    자동
    0.44
    花园
    0.44
    집
    0.44
     famously
    0.43
    Activations Density 0.001%

    No Known Activations