© 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. 90516
    Prev
    Next
    INDEX
    Explanations

    seasonal chill

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

    As discussed

    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
     architects
    0.47
     Dirichlet
    0.45
     creators
    0.45
     നിന്ന്
    0.42
    торая
    0.42
     nguyên
    0.42
    を結
    0.42
    说
    0.42
    共享
    0.41
    টিয়
    0.41
    POSITIVE LOGITS
    especially
    0.46
     осень
    0.46
    ö
    0.44
    ot
    0.44
     infallible
    0.43
     навіть
    0.43
     божо
    0.43
     особенно
    0.42
    autumn
    0.41
     ሁኔታ
    0.41
    Activations Density 0.003%

    No Known Activations