© 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. 143355
    Prev
    Next
    INDEX
    Explanations

    specific times and pages

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

    counting sequence numbers

    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
    賑
    0.43
     Blazer
    0.40
    綏
    0.40
    τώ
    0.39
    𒀝
    0.39
     dipilih
    0.39
     नारा
    0.38
     Kabhi
    0.38
    лиз
    0.38
    rü
    0.38
    POSITIVE LOGITS
     midway
    0.46
    段
    0.46
     końca
    0.45
    쯤
    0.44
    cumsum
    0.43
    结束后
    0.43
    終わり
    0.43
    second
    0.42
    startIndex
    0.40
     koniec
    0.40
    Activations Density 0.023%

    No Known Activations