© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9476
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

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

    urls to download or install

    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
    encrypted
    0.42
     coraz
    0.42
    ವಾಡ
    0.41
    drive
    0.41
     youtube
    0.40
    https
    0.40
    蘚
    0.40
     YouT
    0.40
     ဖ
    0.40
     https
    0.39
    POSITIVE LOGITS
    schemas
    0.46
     Temp
    0.45
    temp
    0.44
    Evans
    0.44
    Temp
    0.43
    GridView
    0.43
    ně
    0.42
    čí
    0.41
    Schemas
    0.40
     vä
    0.40
    Activations Density 0.013%

    No Known Activations