© 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. 209311
    Prev
    Next
    INDEX
    Explanations

    release notes

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

    major release or initial version

    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
     これらの
    0.53
    これらの
    0.51
    它們
    0.49
    陽
    0.47
     부분을
    0.46
    它们的
    0.46
    이니
    0.46
     interrelated
    0.45
    ณ
    0.43
     повіт
    0.43
    POSITIVE LOGITS
     вдох
    0.51
     मदत
    0.49
    ్యంలో
    0.49
     Mehmet
    0.48
     cheeky
    0.48
     Liam
    0.47
     menjual
    0.47
    sendMessage
    0.47
     Thánh
    0.47
     thánh
    0.46
    Activations Density 0.000%

    No Known Activations