© 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. 60154
    Prev
    Next
    INDEX
    Explanations

    phrases like "too funny" or "keep up"

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

    change perspective

    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
    2
    0.49
    却是
    0.48
    ad
    0.48
    س
    0.47
     de
    0.46
    НЕ
    0.46
    ford
    0.44
     تمت
    0.44
    é
    0.44
    易
    0.44
    POSITIVE LOGITS
    orben
    0.48
    tDBOutput
    0.46
    ufieurs
    0.46
    yclerView
    0.46
     queues
    0.46
     lesser
    0.45
    AMPLES
    0.45
     शाळे
    0.45
     آنا
    0.45
    lastval
    0.44
    Activations Density 0.000%

    No Known Activations