© 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. 151070
    Prev
    Next
    INDEX
    Explanations

    Study, follow, auditorium, locations, customize

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

    Fermi problems

    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
     instrument
    0.48
    躯
    0.48
     elution
    0.47
     awaited
    0.45
     dishes
    0.45
     cori
    0.44
     attenuated
    0.44
    heon
    0.42
     upheld
    0.42
    ار
    0.42
    POSITIVE LOGITS
    केवल
    0.52
     atmósfera
    0.49
    .".
    0.48
    Cellphone
    0.48
    ม
    0.48
     realización
    0.47
     quiera
    0.47
    avec
    0.46
    द्वारा
    0.46
    ondon
    0.46
    Activations Density 0.000%

    No Known Activations