© 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. 128001
    Prev
    Next
    INDEX
    Explanations

    gait Will, will give, sensitive adhesive

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

    answering nature or for someone

    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
     ۴
    0.52
     syphilit
    0.50
     kasut
    0.49
     benötigen
    0.49
     rapproche
    0.47
     weeping
    0.47
    ۴
    0.46
     superviv
    0.46
    levance
    0.45
     sobbing
    0.45
    POSITIVE LOGITS
    Motion
    0.45
    मिल
    0.45
    Setting
    0.45
     AUTHOR
    0.44
     yarns
    0.44
     Millions
    0.42
    រ
    0.42
    শিরোনাম
    0.42
     CUSTOM
    0.42
     Setting
    0.42
    Activations Density 0.002%

    No Known Activations