© 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. 9352
    Prev
    Next
    INDEX
    Explanations

    names starting with Jess, Jas, Jes

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

    JavaScript in programming contexts

    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
    Provided
    0.47
     PROVIDED
    0.46
     Provided
    0.42
    ᱚ
    0.41
    ediaan
    0.41
    axial
    0.40
     beside
    0.40
     provided
    0.39
    ഭ്യാ
    0.39
    旁
    0.38
    POSITIVE LOGITS
    TPR
    0.42
    eterminate
    0.38
     ইসলামাবাদ
    0.36
     Jas
    0.36
    ">)</
    0.36
    Jas
    0.35
    getCQL
    0.35
     ká
    0.35
     amine
    0.35
    விக்கும்
    0.35
    Activations Density 0.054%

    No Known Activations