© 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. 87597
    Prev
    Next
    INDEX
    Explanations

    constant child, status LED

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

    perspective on difficulty

    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
    IN
    0.55
    EL
    0.52
    Ä
    0.52
    OM
    0.51
    cpp
    0.48
    ਹੀ
    0.47
    halts
    0.47
     جائیں
    0.46
    OG
    0.46
    α
    0.45
    POSITIVE LOGITS
     Utrecht
    0.50
     Ankara
    0.48
     Hamas
    0.48
     UNI
    0.47
     ሆ
    0.47
     Espresso
    0.46
    ﹁
    0.45
     Bruxelles
    0.44
    ９
    0.44
     Istanbul
    0.43
    Activations Density 0.000%

    No Known Activations