© 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. 83890
    Prev
    Next
    INDEX
    Explanations

    services and amenities

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

    job benefits and work conditions

    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
    瑉
    0.45
    ysts
    0.42
    ій
    0.41
    nější
    0.41
    áciu
    0.41
    është
    0.40
     الموضوع
    0.40
    ังหวัด
    0.38
    owości
    0.38
     इवेंट
    0.38
    POSITIVE LOGITS
    工
    0.41
     monto
    0.40
                
    0.39
     pub
    0.39
    TOK
    0.39
     一
    0.39
     dental
    0.38
    DEST
    0.38
    CONH
    0.37
    Adopt
    0.37
    Activations Density 0.001%

    No Known Activations