© 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. 50134
    Prev
    Next
    INDEX
    Explanations

    monthly newsletter

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

    models, materials, engagement, clarify

    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
     chair
    0.47
    ">&
    0.44
    UIServer
    0.44
     Chair
    0.43
    Chair
    0.43
    πή
    0.42
     безо
    0.40
    椅子
    0.40
    жели
    0.39
    <unused9>
    0.39
    POSITIVE LOGITS
    ellan
    0.48
    ellen
    0.47
    walten
    0.46
    unningham
    0.44
     organelles
    0.43
     lysates
    0.42
     barrios
    0.42
    써
    0.42
     mammalian
    0.42
     comorbidities
    0.42
    Activations Density 0.000%

    No Known Activations