© 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. 26484
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    capture or calculate

    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
     Insurance
    0.43
    ეგი
    0.42
    保险
    0.42
    Listing
    0.42
    Insurance
    0.42
    鹬
    0.40
    विष्ट
    0.40
     Lyndon
    0.40
     হাস
    0.39
    辔
    0.38
    POSITIVE LOGITS
     ausges
    0.57
     unsere
    0.55
     grundsätzlich
    0.54
     précise
    0.52
     لكن
    0.52
     spez
    0.51
    nemen
    0.51
     veröffent
    0.50
     bringen
    0.50
     ausgew
    0.50
    Activations Density 0.000%

    No Known Activations