© 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. 222350
    Prev
    Next
    INDEX
    Explanations

    licensed or endorsed

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

    explaining why something dangerous

    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
     떠
    0.49
     evolucion
    0.44
    กัน
    0.42
     inspiration
    0.40
    ری
    0.39
     LinkedList
    0.39
     팔
    0.39
    smt
    0.39
    สำหรับการ
    0.39
     डाइट
    0.39
    POSITIVE LOGITS
     તમારે
    0.49
     নায়
    0.49
     cashier
    0.47
    whose
    0.46
    besie
    0.46
     cuja
    0.46
     posled
    0.45
    esco
    0.44
     তাঁহার
    0.44
    Վ
    0.44
    Activations Density 0.000%

    No Known Activations