© 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. 78586
    Prev
    Next
    INDEX
    Explanations

    now extended

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

    includes or encapsulates

    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
    :
    0.89
     and
    0.52
    -
    0.52
    ,
    0.51
     và
    0.50
     v
    0.46
     &
    0.46
    3
    0.45
    ;
    0.45
    8
    0.45
    POSITIVE LOGITS
     त्याचा
    0.50
     சிறிய
    0.45
     त्यासाठी
    0.45
     zusätzliche
    0.45
     discernible
    0.45
    ujjati
    0.45
    abhuto
    0.44
     zusätzlichen
    0.44
    潛行
    0.43
    បន្ថែម
    0.43
    Activations Density 0.237%

    No Known Activations