© 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. 126698
    Prev
    Next
    INDEX
    Explanations

    active participants

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

    LittleBigPlanet zones

    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
    ்ட
    0.50
    󠁣
    0.50
    تج
    0.50
    পরিস
    0.50
    সহিত
    0.49
    лм
    0.48
     steered
    0.48
    ლებიც
    0.47
     चार्ट
    0.46
    гот
    0.46
    POSITIVE LOGITS
     amu
    0.55
     M
    0.54
    k
    0.54
    9
    0.54
     E
    0.53
     S
    0.52
     É
    0.52
     l
    0.51
     Workshops
    0.50
     thys
    0.50
    Activations Density 0.000%

    No Known Activations