© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2980
    Prev
    Next
    INDEX
    Explanations

    localhost URLs and MongoDB URIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    Б
    2.36
    Не
    2.06
    К
    2.05
    Й
    2.02
    Μ
    1.97
    Т
    1.96
    Somos
    1.94
    Π
    1.93
    Мо
    1.89
    Bike
    1.88
    POSITIVE LOGITS
    ↵↵
    1.61
     presumably
    1.54
     rudimentary
    1.49
     rung
    1.44
     conceivably
    1.28
     necessitating
    1.28
     ostensibly
    1.25
     subsequent
    1.25
     incurring
    1.24
     unmodified
    1.24
    Activations Density 0.042%

    No Known Activations