© 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. 125991
    Prev
    Next
    INDEX
    Explanations

    fleet maintenance, waiting respectfully, personal loan

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

    lists. "latex" or "image" or "lol"

    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
    قی
    0.53
    𝚘
    0.50
    ச்
    0.48
     பெண்ண
    0.48
    ச்செ
    0.47
    "${
    0.47
     تړل
    0.47
    pieceSelection
    0.46
    indexBuffer
    0.46
     വ്യത്യസ്ത
    0.46
    POSITIVE LOGITS
    s
    0.68
    i
    0.65
    t
    0.61
    d
    0.54
     karna
    0.53
     Hard
    0.51
    y
    0.51
    ↵↵
    0.50
     dermatitis
    0.50
     Mitra
    0.50
    Activations Density 0.001%

    No Known Activations