© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14164
    Prev
    Next
    INDEX
    Explanations

    racing, token, preferred, fit, etiquette, out, collection, stock

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

    conjunctions in multiple languages

    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_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
     stále
    0.50
                     
    0.46
     importancia
    0.45
                         
    0.43
     --------------
    0.43
                                   
    0.42
                      
    0.42
    することも
    0.42
     noviembre
    0.42
    ához
    0.42
    POSITIVE LOGITS
     ಹಾಗೂ
    0.46
    һ
    0.43
     Oreo
    0.41
    하지만
    0.41
    л
    0.40
     Godzilla
    0.40
     Skin
    0.39
     със
    0.39
     East
    0.39
     లేదా
    0.39
    Activations Density 0.016%

    No Known Activations