© 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. 240544
    Prev
    Next
    INDEX
    Explanations

    Published book reading travel

    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
     ponctué
    0.51
     fazia
    0.51
    居家
    0.50
     ponctuées
    0.50
     líng
    0.48
    彷
    0.48
    滔
    0.46
    ।’
    0.46
     demasi
    0.45
     effectué
    0.45
    POSITIVE LOGITS
     Ambassadors
    0.49
     airways
    0.45
     थोड़ी
    0.45
     Zeus
    0.45
     American
    0.45
     Silverstone
    0.44
     Vanderbilt
    0.44
     ambassadors
    0.44
     Athletics
    0.43
    ΟΣ
    0.43
    Activations Density 0.000%

    No Known Activations