© 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. 224499
    Prev
    Next
    INDEX
    Explanations

    under section

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

    defining spectrum of meaning

    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
     یق
    0.64
    १
    0.54
    gaussian
    0.54
    등
    0.54
     لڑکی
    0.53
    ग
    0.53
    ম
    0.53
    얼
    0.53
    дт
    0.51
    Ż
    0.51
    POSITIVE LOGITS
     ‘
    0.53
     “
    0.51
     ;(
    0.49
     Vehicle
    0.48
     Wells
    0.48
     +,
    0.47
     ;$
    0.46
    ’;
    0.45
     GM
    0.45
     ২৪
    0.44
    Activations Density 0.001%

    No Known Activations