© 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. 135076
    Prev
    Next
    INDEX
    Explanations

    packaging design

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

    balancing or explaining contradictions

    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
    handling
    0.42
    \
    0.41
    abdominal
    0.41
    בים
    0.40
    جر
    0.39
    (
    0.39
    ₱
    0.39
    لاً
    0.39
    ating
    0.38
     handle
    0.38
    POSITIVE LOGITS
     Bugünkü
    0.65
     уте
    0.52
     Teb
    0.48
    のス
    0.48
     Tets
    0.48
    വരെ
    0.48
     Marxist
    0.48
     запрос
    0.48
     や
    0.47
     Hermes
    0.47
    Activations Density 0.000%

    No Known Activations