© 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. 158439
    Prev
    Next
    INDEX
    Explanations

    locations and activities

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

    specific words and numbers

    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
    s
    0.53
     juridique
    0.50
     tumeur
    0.49
     graisse
    0.48
     نمبر
    0.47
     علامه
    0.47
    с
    0.46
     glance
    0.45
     hals
    0.45
    স
    0.45
    POSITIVE LOGITS
    今
    0.46
    西班牙
    0.46
     Active
    0.45
     visits
    0.45
     Adventure
    0.44
    abil
    0.43
    jó
    0.43
     adventure
    0.43
    ery
    0.43
    他的
    0.43
    Activations Density 0.000%

    No Known Activations