© 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. 16476
    Prev
    Next
    INDEX
    Explanations

    are confused or viewing

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

    rarity and vapor

    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
    ']+
    0.47
    ¹
    0.46
    身材
    0.46
     pozit
    0.45
     örne
    0.44
    ']=
    0.42
    ₁+
    0.42
    '][
    0.42
    ərbay
    0.42
     lục
    0.41
    POSITIVE LOGITS
    ofSeconds
    0.41
    ort
    0.40
     swiftly
    0.40
    רה
    0.39
    apan
    0.38
    uala
    0.38
     એલ
    0.38
    anning
    0.38
    上げて
    0.38
     Build
    0.37
    Activations Density 0.000%

    No Known Activations