© 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. 190124
    Prev
    Next
    INDEX
    Explanations

    special mentions

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

    product announcements

    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
     Monet
    0.46
     Pix
    0.44
     multitude
    0.43
     Far
    0.43
     pathetic
    0.42
    Platform
    0.42
     Farah
    0.42
    松
    0.41
    Mah
    0.41
     фар
    0.41
    POSITIVE LOGITS
     indique
    0.54
     indiqu
    0.51
     レッド
    0.49
    บ่ง
    0.48
     privind
    0.48
    ية
    0.47
     aunque
    0.47
     iako
    0.47
     رغم
    0.47
     dispone
    0.47
    Activations Density 0.001%

    No Known Activations