© 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. 17577
    Prev
    Next
    INDEX
    Explanations

    locations and services

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

    worldwide systems

    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
     Y
    0.42
     №
    0.39
     borrowed
    0.38
     ৪
    0.37
     admit
    0.36
     inherited
    0.36
     Q
    0.36
     $(
    0.35
     Beijing
    0.35
     ∈
    0.35
    POSITIVE LOGITS
    宗旨
    0.44
    Roche
    0.44
    职责
    0.44
    物资
    0.42
    ስቃ
    0.42
    managers
    0.40
    كمان
    0.40
    स्थापन
    0.40
    廪
    0.40
    commod
    0.39
    Activations Density 0.000%

    No Known Activations