© 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. 95028
    Prev
    Next
    INDEX
    Explanations

    inquiries, required, travelled

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

    collaboration, ML, and savings

    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
    ப்பிர
    0.52
     has
    0.49
    has
    0.46
    There
    0.46
    ก
    0.45
    هی
    0.44
    astic
    0.43
    Has
    0.43
    Throughout
    0.43
    ה
    0.42
    POSITIVE LOGITS
     Koordin
    0.49
    的应用
    0.49
     Productos
    0.47
     Operations
    0.46
     cytokine
    0.46
     Ambient
    0.46
     outsource
    0.45
     Contributions
    0.45
    }/{
    0.44
    anos
    0.44
    Activations Density 0.001%

    No Known Activations