© 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. 206288
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    sequences around punctuation

    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
     compara
    0.54
    ꞎ
    0.52
     존
    0.50
     placent
    0.48
     rhiz
    0.47
     वोटों
    0.47
     सी
    0.47
     戸
    0.47
     प्ल
    0.47
     hort
    0.46
    POSITIVE LOGITS
    ում
    0.50
     নেতাকর্মীরা
    0.42
    સર
    0.41
    撤
    0.40
    跹
    0.39
    Während
    0.39
    ZIE
    0.39
    靥
    0.38
     --
    0.38
     –
    0.38
    Activations Density 0.001%

    No Known Activations