© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12048
    Prev
    Next
    INDEX
    Explanations

    async operations

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

    code constructs and function calls

    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_31_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
     Эта
    0.40
    𝘮
    0.40
     あなた
    0.39
     år
    0.38
    𝘬
    0.37
     आपल्याला
    0.37
     बिटकॉइन
    0.37
    이렇게
    0.37
    ０
    0.37
     ബോ
    0.37
    POSITIVE LOGITS
    ECC
    0.40
    CHEC
    0.38
    حي
    0.35
     reto
    0.35
    Rue
    0.35
     adsorb
    0.35
    INER
    0.34
    INDE
    0.33
    Lambert
    0.33
     Carr
    0.33
    Activations Density 0.000%

    No Known Activations