© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12247
    Prev
    Next
    INDEX
    Explanations

    exist

    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
     dihad
    1.80
     вообще
    1.69
     لگ
    1.66
     intégr
    1.61
    طب
    1.61
    <0xE2>
    1.54
     aggior
    1.53
    غ
    1.50
     concor
    1.47
     облада
    1.46
    POSITIVE LOGITS
     roadway
    2.23
    jecture
    2.11
     sects
    2.10
    entious
    2.09
     laborers
    2.04
    avorable
    2.01
    stArray
    1.95
    '`--
    1.94
     노
    1.94
     오류
    1.92
    Activations Density 2.208%

    No Known Activations