© 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. 3165
    Prev
    Next
    INDEX
    Explanations

    code of

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

    measurement unit conversion

    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
    <unused12>
    0.51
    րան
    0.51
    י
    0.50
    लन
    0.48
    <unused39>
    0.47
    <unused30>
    0.46
     प्रदेश
    0.46
     አለበት
    0.45
     ছাপা
    0.45
    Vaterpolo
    0.45
    POSITIVE LOGITS
     which
    0.67
    ,
    0.64
     as
    0.58
     (<
    0.54
     (£
    0.52
     ($
    0.50
    *,
    0.50
    ،
    0.49
     (“
    0.48
     ("
    0.48
    Activations Density 0.000%

    No Known Activations