© 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. 241634
    Prev
    Next
    INDEX
    Explanations

    planning and dates

    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
    面包
    0.51
    Doctors
    0.48
    刚刚
    0.46
    愴
    0.46
    Tiny
    0.45
     ছি
    0.45
     ponctuées
    0.44
    从而
    0.43
    珵
    0.43
     মায়
    0.43
    POSITIVE LOGITS
     heatmap
    0.51
    pipeline
    0.50
     Hindustan
    0.50
    bf
    0.50
     DNN
    0.49
     BI
    0.49
    il
    0.48
    ident
    0.48
    bm
    0.48
    im
    0.47
    Activations Density 0.001%

    No Known Activations