© 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. 197638
    Prev
    Next
    INDEX
    Explanations

    thou multiplied, are grouped, non-, 2Cor, bad memories, small dumpster

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

    future actions or explanations

    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
    im
    0.55
     to
    0.54
    ca
    0.54
    9
    0.52
    la
    0.51
    ita
    0.51
    何の
    0.48
    7
    0.48
    help
    0.48
    ▪
    0.46
    POSITIVE LOGITS
    ግዳ
    0.46
    дуу
    0.45
    ുകളും
    0.45
    សម
    0.43
     version
    0.43
    తంగా
    0.43
    股市
    0.43
     Capacity
    0.43
     రోజుల
    0.43
     মূর্তি
    0.42
    Activations Density 0.000%

    No Known Activations