© 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. 114829
    Prev
    Next
    INDEX
    Explanations

    modified situations or events

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

    big tiddy xenomorph

    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
    虔
    0.44
    西兰
    0.43
     Magnus
    0.43
     Britton
    0.43
     Ops
    0.42
     Splits
    0.42
     Dorothe
    0.42
     Bogdan
    0.41
     Noyes
    0.41
     Operators
    0.41
    POSITIVE LOGITS
    HTMLElement
    0.50
    ﺩ
    0.46
    ເນ
    0.44
    InterfaceLine
    0.43
    VARIABLE
    0.43
     महत्त्वपूर्ण
    0.43
    lastname
    0.43
    tdd
    0.43
    essentially
    0.43
    
    0.42
    Activations Density 0.000%

    No Known Activations