© 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. 31652
    Prev
    Next
    INDEX
    Explanations

    place names and numbers

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

    Japanese honorifics and speech particles

    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
     ez
    0.49
     Ro
    0.48
     EZ
    0.48
     W
    0.48
     Eg
    0.47
     Z
    0.47
     Es
    0.46
     And
    0.45
     ew
    0.45
    ik
    0.45
    POSITIVE LOGITS
    ❽
    0.55
    اسلام
    0.51
    ཥ
    0.49
    ূর
    0.48
    ␊
    0.48
    reflectionMap
    0.48
    ાર્થના
    0.47
    Ⲏ
    0.47
     construção
    0.46
    ׄ
    0.46
    Activations Density 0.000%

    No Known Activations