© 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. 34448
    Prev
    Next
    INDEX
    Explanations

    time and home locations

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

    radius, library, fitness, tune

    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
     nosso
    0.51
    其实
    0.49
     nossa
    0.45
     our
    0.45
     actually
    0.44
    =
    0.44
    :
    0.44
     res
    0.44
    系统
    0.43
    ：
    0.42
    POSITIVE LOGITS
    <unused2115>
    0.46
    ⁄
    0.45
     đựng
    0.43
     சோதனை
    0.42
     ステンレス
    0.41
    <unused12>
    0.41
    とのこと
    0.41
    __."
    0.41
    企画
    0.40
    ాలంటే
    0.40
    Activations Density 0.000%

    No Known Activations