© 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. 51728
    Prev
    Next
    INDEX
    Explanations

    numbers and quantity indicators

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

    'grab a', 'what make', 'not doing', 'return items'

    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
    
    0.52
     ಅನುಪಾತ
    0.46
    Ze
    0.44
    glass
    0.43
    heng
    0.43
    chips
    0.42
    dür
    0.41
    Graph
    0.40
    澤
    0.40
    ze
    0.40
    POSITIVE LOGITS
     showbiz
    0.54
     localização
    0.51
     cinco
    0.50
     todas
    0.49
     Herpes
    0.47
    τός
    0.46
     localidades
    0.46
    циям
    0.46
     motoc
    0.46
     passa
    0.45
    Activations Density 0.000%

    No Known Activations