© 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. 72907
    Prev
    Next
    INDEX
    Explanations

    awards, prizes, languages

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

    security and ethical concerns

    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
    ва
    0.50
     hello
    0.46
     nitrile
    0.44
    確
    0.44
    ijek
    0.44
     mounds
    0.43
    hello
    0.43
    難
    0.43
    ре
    0.43
    го
    0.42
    POSITIVE LOGITS
     शताब्दी
    0.47
     Premio
    0.43
     இளம்
    0.43
    স্কার
    0.43
     कमेंट
    0.43
     संबंधी
    0.43
    ̦
    0.43
     તમને
    0.42
     prevenir
    0.42
     વિશે
    0.42
    Activations Density 0.001%

    No Known Activations