© 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. 97001
    Prev
    Next
    INDEX
    Explanations

    employees, dormitories, Insolvency

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

    environmental or data sources

    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
     pediatrician
    0.52
    返す
    0.48
     mathematician
    0.46
     மருத்து
    0.46
     factorización
    0.45
     d
    0.45
     comma
    0.44
     darn
    0.44
    げ
    0.44
     newline
    0.43
    POSITIVE LOGITS
    Extern
    0.49
    TrackAngle
    0.49
    Proc
    0.48
     AppPage
    0.47
     Kegiatan
    0.47
    integral
    0.46
     İlçesi
    0.46
     PROC
    0.46
     Ecosystem
    0.46
     Proc
    0.46
    Activations Density 0.000%

    No Known Activations