© 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. 8718
    Prev
    Next
    INDEX
    Explanations

    mounts, brackets, or pendants

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

    mounts, brackets, and supports

    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
     lids
    0.50
     linings
    0.46
    捂
    0.44
     baggy
    0.43
    密封
    0.43
     seals
    0.41
     coverings
    0.41
     shredded
    0.41
     lid
    0.41
    封
    0.40
    POSITIVE LOGITS
     mounting
    1.49
     mount
    1.44
     mounts
    1.39
     Mounting
    1.38
    mounting
    1.32
     bracket
    1.31
    Mount
    1.24
     Bracket
    1.23
     brackets
    1.23
    bracket
    1.22
    Activations Density 0.686%

    No Known Activations