© 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. 84335
    Prev
    Next
    INDEX
    Explanations

    enormous amount

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

    tutorials and examples

    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
     täglich
    0.49
     jährlich
    0.46
     impoverished
    0.46
     Physik
    0.44
     onc
    0.44
    
    0.44
     gravid
    0.43
    頻
    0.43
     propio
    0.42
     ataupun
    0.42
    POSITIVE LOGITS
    電影
    0.50
    ही
    0.45
    กก
    0.44
    akkam
    0.44
    <0xA0>
    0.43
    netflix
    0.43
    usega
    0.42
     영화
    0.42
    complete
    0.41
     кры
    0.41
    Activations Density 0.001%

    No Known Activations