© 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. 23501
    Prev
    Next
    INDEX
    Explanations

    information on, proud of, year's, plans Date

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

    mathematical expression calculation

    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
     Św
    0.52
     Warfare
    0.50
     Acids
    0.48
    Ἄ
    0.47
     जड़ों
    0.47
    ường
    0.47
     Wanna
    0.47
     waxes
    0.46
    게
    0.46
     reigned
    0.46
    POSITIVE LOGITS
     esclare
    0.46
     BRIDGE
    0.45
     संघ
    0.45
     VILL
    0.45
     MISS
    0.45
     vot
    0.44
     broiler
    0.44
     dihad
    0.43
    вам
    0.43
     MILL
    0.42
    Activations Density 0.000%

    No Known Activations