© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7093
    Prev
    Next
    INDEX
    Explanations

    south zone of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
    нести
    0.56
    ятся
    0.51
    रोवर
    0.51
     నగ
    0.51
    сель
    0.50
     арифмети
    0.50
    வ்வ
    0.49
    
    0.49
    ‍ह
    0.49
    雫
    0.47
    POSITIVE LOGITS
     Regional
    0.58
     regional
    0.54
    Regional
    0.52
     sprach
    0.52
     Reporter
    0.50
     Tf
    0.50
     আঞ্চলিক
    0.50
     semin
    0.49
     residual
    0.49
     bapt
    0.48
    Activations Density 0.197%

    No Known Activations