© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11346
    Prev
    Next
    INDEX
    Explanations

    Cab leading to words

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

    cab or kab prefixes

    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_40_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
    trans
    0.45
    utant
    0.43
    ุป
    0.41
    mers
    0.40
    usen
    0.38
    endien
    0.38
    hers
    0.38
    <0xAB>
    0.38
    untary
    0.38
    mtext
    0.37
    POSITIVE LOGITS
    Cab
    0.83
     CAB
    0.81
     Cab
    0.79
     cab
    0.78
    CAB
    0.72
    cab
    0.71
     Cabot
    0.71
    Kab
    0.65
     cabe
    0.61
     kab
    0.60
    Activations Density 0.080%

    No Known Activations