© 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. 41763
    Prev
    Next
    INDEX
    Explanations

    preposition + noun/determiner

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

    refusal of inappropriate requests

    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
     '
    0.52
    entar
    0.51
     Entropy
    0.48
    ukaemia
    0.46
     euros
    0.44
     Eur
    0.44
     ENT
    0.44
     euro
    0.44
     Opening
    0.43
    enture
    0.43
    POSITIVE LOGITS
     độ
    0.46
    தன்
    0.45
    笉
    0.45
    继承
    0.44
    峯
    0.44
    สอบ
    0.43
    τί
    0.43
    פון
    0.43
     ছোট
    0.43
     hướng
    0.42
    Activations Density 0.000%

    No Known Activations