© 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. 137617
    Prev
    Next
    INDEX
    Explanations

    updates about

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

    conditional logic

    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
     आधा
    0.48
    üşt
    0.47
    inputStream
    0.47
     बंदूक
    0.46
    مون
    0.46
    謦
    0.46
    被害
    0.46
    cute
    0.45
    ograma
    0.45
    인다
    0.43
    POSITIVE LOGITS
     conversely
    0.49
              
    0.47
     Phillips
    0.46
     Bergeron
    0.45
     on
    0.45
    0.45
            
    0.44
    Sementara
    0.44
    0.44
    Alternatively
    0.44
    Activations Density 0.001%

    No Known Activations