© 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. 12913
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    breakdown of

    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
    u
    0.09
    ak
    0.09
    ij
    0.07
    ue
    0.07
    ud
    0.07
    ốt
    0.07
    uspended
    0.07
    onClick
    0.06
    leetcode
    0.06
    পাড়
    0.06
    POSITIVE LOGITS
     スト
    0.07
     праз
    0.07
     보는
    0.07
     제작
    0.07
     инте
    0.07
     livello
    0.07
     민
    0.07
     보다
    0.07
    𝘱
    0.07
     ми
    0.07
    Activations Density 0.001%

    No Known Activations