© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 95468
    Prev
    Next
    INDEX
    Explanations

    urban areas

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

    places or locations

    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
     modificare
    0.52
     sanc
    0.50
     dificult
    0.48
    يمان
    0.48
    тинг
    0.47
    担
    0.46
     claridad
    0.46
    监管
    0.46
     oblic
    0.45
    ).$$
    0.45
    POSITIVE LOGITS
     Index
    0.49
    te
    0.48
     Writer
    0.48
    est
    0.46
     Week
    0.45
    lax
    0.44
    er
    0.44
     Resources
    0.44
    qz
    0.44
     Zwe
    0.44
    Activations Density 0.000%

    No Known Activations