© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1870
    Prev
    Next
    INDEX
    Explanations

    improvements and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Glaub
    1.80
     Pusat
    1.76
     آتی
    1.72
    浼
    1.70
    시에
    1.69
    arına
    1.69
     Woodstock
    1.67
    ศึกษา
    1.66
    cknow
    1.65
     Arma
    1.65
    POSITIVE LOGITS
     shutout
    1.18
    cards
    1.13
     against
    1.12
    heets
    1.11
    assisted
    1.01
    heet
    0.95
    險
    0.95
     versus
    0.92
    card
    0.92
    oliath
    0.92
    Activations Density 0.339%

    No Known Activations