© 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. 8617
    Prev
    Next
    INDEX
    Explanations

    words followed by grammatical function

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

    terms and conditions

    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
    緎
    0.41
    䄪
    0.41
     ప్రక
    0.40
     स्थानिक
    0.39
     कृष्णा
    0.38
     örg
    0.37
    筤
    0.37
    멩
    0.37
     राजवंश
    0.37
     వర్
    0.37
    POSITIVE LOGITS
    +
    0.44
    beta
    0.43
    ,
    0.42
    +,
    0.42
    for
    0.41
    *
    0.41
    tr
    0.40
    =>
    0.38
    b
    0.38
    ut
    0.38
    Activations Density 0.023%

    No Known Activations