© 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. 9802
    Prev
    Next
    INDEX
    Explanations

    go to, come to, look at

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

    Amsterdam, Texel, Dutch, German

    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
     ASPECTS
    0.46
    കല
    0.46
    Reprodu
    0.42
     Reproductive
    0.41
     membentuk
    0.39
    似的
    0.39
    謦
    0.38
     van
    0.38
     literatura
    0.38
     seide
    0.38
    POSITIVE LOGITS
     ls
    0.42
    Gut
    0.40
    CIP
    0.39
     Mois
    0.39
     Gut
    0.38
    𝐺
    0.38
    áb
    0.37
     Trent
    0.37
     Ug
    0.37
     cowboy
    0.37
    Activations Density 0.055%

    No Known Activations