© 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. 1978
    Prev
    Next
    INDEX
    Explanations

    hormonal and physical properties

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

    measurement of states and quantities

    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
    狲
    0.33
    驷
    0.32
     şirket
    0.31
     ülk
    0.30
    侪
    0.30
    ंसारी
    0.29
     چیز
    0.29
    诡
    0.29
    纭
    0.29
    摈
    0.29
    POSITIVE LOGITS
     from
    0.46
     of
    0.42
    based
    0.40
     during
    0.40
     on
    0.38
     generated
    0.38
     versus
    0.38
     using
    0.37
    from
    0.36
     based
    0.36
    Activations Density 0.224%

    No Known Activations