© 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-262K
    7. 80093
    Prev
    Next
    INDEX
    Explanations

    detecting updates and next steps

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

    viewport width parameter

    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_262k_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
     kn
    0.45
     ▪
    0.43
     with
    0.42
     u
    0.42
     Hotel
    0.41
     City
    0.41
     WITH
    0.41
     kilowatt
    0.41
     o
    0.41
     ste
    0.40
    POSITIVE LOGITS
    ១
    0.48
    istically
    0.48
    LinkedList
    0.48
    𒁹
    0.46
    autoprefixer
    0.45
    푀
    0.45
    Mannschaft
    0.44
    ίζεται
    0.44
    ヤモンド
    0.44
    apayati
    0.43
    Activations Density 0.000%

    No Known Activations