© 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. 70412
    Prev
    Next
    INDEX
    Explanations

    lists of things

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

    setting environment variables

    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
    )
    0.46
     trek
    0.46
    "
    0.45
     Estate
    0.44
    Estate
    0.43
    R
    0.43
    ‍
    0.43
     TRAN
    0.42
    TRAN
    0.42
    광
    0.42
    POSITIVE LOGITS
     හෝ
    0.50
     Webseite
    0.49
     Leibn
    0.48
    eres
    0.46
     सूचीबद्ध
    0.46
     සෑම
    0.46
     सचिव
    0.46
     skrev
    0.45
     hetzelfde
    0.45
    ỏe
    0.44
    Activations Density 0.000%

    No Known Activations