© 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. 80749
    Prev
    Next
    INDEX
    Explanations

    multilingual words

    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
    w
    0.54
            
    0.53
    #
    0.53
    eg
    0.50
    TODO
    0.50
     Eğer
    0.48
                
    0.48
    0.47
     Crear
    0.47
    creator
    0.46
    POSITIVE LOGITS
     žiad
    0.51
     oyster
    0.49
     oysters
    0.48
    ણમાં
    0.45
    ولندا
    0.45
     phosphatase
    0.43
     žád
    0.43
     aberration
    0.42
    脐
    0.42
    পা
    0.41
    Activations Density 0.000%

    No Known Activations