© 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. 251622
    Prev
    Next
    INDEX
    Explanations

    punctuation and foreign words

    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
    icultural
    0.45
    лер
    0.41
     इंडियन
    0.41
     RICH
    0.40
     Morgan
    0.40
    Jam
    0.39
    னுடைய
    0.39
    ృ
    0.39
    opedic
    0.39
     ఇండి
    0.38
    POSITIVE LOGITS
    !”
    0.53
    !\
    0.50
    !”,
    0.50
     unlocks
    0.49
     giữ
    0.48
    !?
    0.48
     prób
    0.48
     đủ
    0.47
    躹
    0.47
     và
    0.46
    Activations Density 0.001%

    No Known Activations