© 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. 18015
    Prev
    Next
    INDEX
    Explanations

    video content

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

    video lectures or lessons

    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
     Schottky
    0.38
    PARTY
    0.37
     uncharted
    0.36
     sepak
    0.34
     PARTY
    0.33
    ဿ
    0.33
     Party
    0.33
     undamaged
    0.33
    ほぼ
    0.33
     peraturan
    0.33
    POSITIVE LOGITS
    こういう
    0.56
    怎么
    0.49
    语音
    0.49
    我说
    0.48
     cantar
    0.48
     and
    0.47
    求解
    0.47
     الصوت
    0.47
    解答
    0.46
    我
    0.46
    Activations Density 0.000%

    No Known Activations