© 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. 154217
    Prev
    Next
    INDEX
    Explanations

    formal letters, income, Rule Set, cities

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

    best possible 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
     amortization
    0.51
    لاك
    0.49
     cooper
    0.46
    祿
    0.46
     reallocation
    0.46
     division
    0.44
     acetonitrile
    0.43
     eenvoudig
    0.43
     automotive
    0.42
     geometries
    0.42
    POSITIVE LOGITS
    ul
    0.52
     Jews
    0.50
    ۀ
    0.50
     Muslims
    0.49
     Vide
    0.47
    vider
    0.47
     Muslim
    0.46
    luž
    0.45
     Passion
    0.44
    ad
    0.44
    Activations Density 0.001%

    No Known Activations