© 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. 104033
    Prev
    Next
    INDEX
    Explanations

    place names

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

    financial systems and control

    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
     iconic
    0.47
    α
    0.46
     grassroots
    0.46
    シェア
    0.46
     theme
    0.45
    sheet
    0.45
    solar
    0.44
     war
    0.43
     subscribers
    0.43
     shrub
    0.42
    POSITIVE LOGITS
    蓖
    0.50
    仳
    0.49
     बीएसटीसी
    0.48
    让我
    0.47
    的学生
    0.47
    غان
    0.46
     calculado
    0.46
    澧
    0.46
    ລັບ
    0.46
    兰
    0.46
    Activations Density 0.000%

    No Known Activations