© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 69337
    Prev
    Next
    INDEX
    Explanations

    the Japanese period followed by sentence starters

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

    Japanese text, especially dialogue or explanations

    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
    नाल्ड
    0.74
    ोलिक
    0.70
    सामान्यीकृत
    0.70
    ısına
    0.70
    landı
    0.69
    ऊदी
    0.69
    ِي
    0.69
     başka
    0.68
    िना
    0.68
    तीने
    0.68
    POSITIVE LOGITS
     「
    0.95
    その
    0.84
    ただし
    0.82
    これから
    0.82
    そして
    0.80
    「
    0.79
    お
    0.77
     ※
    0.77
    これは
    0.77
    この
    0.75
    Activations Density 0.021%

    No Known Activations