© 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. 208869
    Prev
    Next
    INDEX
    Explanations

    copyright and technical terms

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

    technical function calls

    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
     fournisseurs
    0.48
    艨
    0.47
     ulei
    0.46
     विश्
    0.46
    achievement
    0.45
     proyek
    0.45
     envol
    0.45
    瞟
    0.45
     ビタミン
    0.45
    chema
    0.44
    POSITIVE LOGITS
    зо
    0.49
    م
    0.47
    كم
    0.46
    Comple
    0.43
    Reading
    0.42
    Kn
    0.42
    স্থ
    0.41
    തില്‍
    0.41
    Handler
    0.41
    Readme
    0.41
    Activations Density 0.000%

    No Known Activations