© 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. 2181
    Prev
    Next
    INDEX
    Explanations

    state or placement

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

    how something is made or done

    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
    。
    0.20
    但这
    0.18
    。「
    0.17
    ។
    0.17
    。“
    0.16
     ซึ่ง
    0.16
    。.
    0.15
    ®.
    0.14
    。"
    0.14
    和
    0.14
    POSITIVE LOGITS
     on
    0.25
     in
    0.24
     исключительно
    0.24
    in
    0.24
     from
    0.23
     wyłącznie
    0.23
     exclusively
    0.21
     primarily
    0.21
     only
    0.21
     within
    0.21
    Activations Density 1.000%

    No Known Activations