© 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. 194858
    Prev
    Next
    INDEX
    Explanations

    tours

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

    exploring requests and specific details

    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
    С
    0.56
    Об
    0.49
     accel
    0.49
     LEDs
    0.48
    韓国
    0.48
     eukaryotes
    0.48
     HOUR
    0.47
    ;"
    0.46
    ച
    0.46
     PRIM
    0.46
    POSITIVE LOGITS
    Corp
    0.52
    ानगर
    0.51
    Strain
    0.51
    ור
    0.47
    Tested
    0.46
    Trou
    0.46
    Tran
    0.46
    rieve
    0.45
    ISH
    0.45
    PhotoMode
    0.45
    Activations Density 0.001%

    No Known Activations