© 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. 197882
    Prev
    Next
    INDEX
    Explanations

    trolling for, smallmouth

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

    different choices and circumstances

    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
     not
    0.57
     七
    0.54
     ۷
    0.51
    ne
    0.48
     plus
    0.48
     gladly
    0.48
     th
    0.48
     نه
    0.47
     더
    0.47
    ۷
    0.47
    POSITIVE LOGITS
    獭
    0.48
    LAGAB
    0.46
    Sexy
    0.46
    Sexual
    0.45
    Creo
    0.45
    Бар
    0.45
    SRP
    0.45
    きた
    0.45
    Sci
    0.45
    SampleSize
    0.44
    Activations Density 0.001%

    No Known Activations