© 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. 244653
    Prev
    Next
    INDEX
    Explanations

    kids with IBD

    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
    帮助
    0.44
    难度
    0.44
    ്ര
    0.42
     Hoffnung
    0.42
     week
    0.42
    룰
    0.41
     Deadpool
    0.40
    n
    0.40
     schwier
    0.40
     NSFW
    0.40
    POSITIVE LOGITS
     кине
    0.46
    щини
    0.46
                        
    0.44
    快適
    0.44
     enrolled
    0.44
     বালক
    0.44
    TabStop
    0.44
     линии
    0.43
                            
    0.43
    ambiental
    0.42
    Activations Density 0.001%

    No Known Activations