© 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. 99025
    Prev
    Next
    INDEX
    Explanations

    personal use only

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

    establishing requirements or setting context

    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
     நிமிடங்கள்
    0.47
    ämän
    0.46
    ynı
    0.45
    வருக்கும்
    0.44
    mity
    0.44
     கெல்வின்
    0.43
     минуты
    0.43
    萜
    0.43
    drž
    0.42
     ट्रायंगल
    0.42
    POSITIVE LOGITS
     boom
    0.49
     refin
    0.47
     poo
    0.46
     investor
    0.45
     igen
    0.45
     investors
    0.44
     unassuming
    0.44
     edit
    0.44
     bali
    0.44
     space
    0.44
    Activations Density 0.001%

    No Known Activations