© 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. 77644
    Prev
    Next
    INDEX
    Explanations

    locations, descriptions, or specific entities

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

    problematic or awkward phrasing

    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
    S
    0.59
    Y
    0.57
    س
    0.57
    Z
    0.55
    J
    0.53
    B
    0.50
    V
    0.50
    L
    0.48
     s
    0.46
    s
    0.46
    POSITIVE LOGITS
     соединения
    0.48
    issements
    0.48
    hältnis
    0.47
     ребенка
    0.47
    IamPermissions
    0.46
     ہوتی
    0.46
     выдви
    0.46
     νέ
    0.46
     அரசிய
    0.45
     εφαρ
    0.45
    Activations Density 0.004%

    No Known Activations