© 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. 67329
    Prev
    Next
    INDEX
    Explanations

    PAST PROGRAM

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

    directions, links, configuration

    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
     bellissimo
    0.52
     decorative
    0.51
     suport
    0.50
     제
    0.48
     beats
    0.47
     superhero
    0.47
    in
    0.47
     prophets
    0.46
     framework
    0.46
     barbeque
    0.46
    POSITIVE LOGITS
     Vascular
    0.52
    PatientR
    0.51
     عليكم
    0.49
    اللي
    0.48
    yta
    0.48
     أوروبا
    0.47
     Ferry
    0.46
    filer
    0.46
    姒
    0.46
     بەر
    0.46
    Activations Density 0.000%

    No Known Activations