© 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. 190114
    Prev
    Next
    INDEX
    Explanations

    financial or descriptive contexts

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

    run in

    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
     ব্যয়
    0.56
     Política
    0.53
     î
    0.52
     ລັບ
    0.51
    
    0.48
    ፡፡
    0.47
     súa
    0.46
     તેમ
    0.46
     编辑
    0.46
     señal
    0.45
    POSITIVE LOGITS
    angels
    0.51
    credible
    0.50
    誤
    0.49
     animals
    0.47
     philosophers
    0.47
    いわ
    0.47
     agendas
    0.47
     egregious
    0.46
    ス
    0.46
    나
    0.46
    Activations Density 0.001%

    No Known Activations