© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8090
    Prev
    Next
    INDEX
    Explanations

    proper names and titles

    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_13_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
     J
    1.18
    博士
    1.01
    ,
    0.97
     eds
    0.93
     nació
    0.93
     Cities
    0.93
     PhD
    0.92
     Law
    0.92
     née
    0.92
     于
    0.92
    POSITIVE LOGITS
    examtype
    1.36
    <unused298>
    1.27
    ParameterActive
    1.21
    FAST
    1.20
    reactivex
    1.18
    idenav
    1.18
    trending
    1.17
    <unused681>
    1.15
    embeddings
    1.15
    Uppercase
    1.14
    Activations Density 0.257%

    No Known Activations