© 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. 14346
    Prev
    Next
    INDEX
    Explanations

    nearby amenities and walking distance

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

    locations and public services

    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
     divergent
    0.41
     \%
    0.40
     recid
    0.39
     categorical
    0.39
     arouse
    0.39
     categorically
    0.39
     deltaTime
    0.39
     वर्गीकृत
    0.38
     LENGTH
    0.37
     Eigenschaften
    0.37
    POSITIVE LOGITS
     arm
    0.40
     barrister
    0.39
    onte
    0.39
     الجنوب
    0.39
     七
    0.38
    cca
    0.37
     אבי
    0.37
     Incub
    0.37
    ônica
    0.37
    flake
    0.37
    Activations Density 0.001%

    No Known Activations