© 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. 168826
    Prev
    Next
    INDEX
    Explanations

    Purchase agreement

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

    often recommend or usually describe

    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
    ﺔ
    0.46
     Gober
    0.44
    abetic
    0.43
     Fiber
    0.43
     ='
    0.43
     Spread
    0.42
    :~
    0.42
    Sat
    0.42
    Uncle
    0.42
    Fiber
    0.42
    POSITIVE LOGITS
     follicular
    0.50
     \%)$
    0.48
     subpar
    0.47
     pili
    0.47
     condiment
    0.46
     vestib
    0.46
     havde
    0.46
     odio
    0.45
     proje
    0.45
     saluran
    0.44
    Activations Density 0.002%

    No Known Activations