© 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. 8727
    Prev
    Next
    INDEX
    Explanations

    operating conference, pays bills, children's space

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

    describes, fluids, knowledge, ties, landing

    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
     Cocktail
    0.43
    ্ল্ড
    0.41
     коктей
    0.40
    емый
    0.39
    캣
    0.38
     Tomcat
    0.38
    ્લા
    0.38
     MALL
    0.37
    Ignore
    0.37
     드러
    0.37
    POSITIVE LOGITS
    )|
    0.53
    itect
    0.42
     architect
    0.42
    ifi
    0.41
    |-
    0.41
    peri
    0.41
    astere
    0.40
    rog
    0.39
    ilin
    0.39
    ias
    0.38
    Activations Density 0.000%

    No Known Activations