© 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. 76713
    Prev
    Next
    INDEX
    Explanations

    population counts in millions

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

    million people

    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
    होत
    0.41
    ESTIC
    0.40
    effici
    0.40
    Illegal
    0.40
    কাঁ
    0.40
    Ꮭ
    0.40
    ड़ाई
    0.40
    friends
    0.39
     fuese
    0.39
     femei
    0.39
    POSITIVE LOGITS
    table
    0.42
    تون
    0.40
     clasp
    0.40
     Einführung
    0.40
     tàu
    0.39
     REM
    0.39
    水道
    0.39
     d
    0.39
     Kähler
    0.38
     besch
    0.38
    Activations Density 0.000%

    No Known Activations