© 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. 12478
    Prev
    Next
    INDEX
    Explanations

    Grain Deal, self, map, tireless, cómodo

    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
    祕
    1.32
     complètement
    1.25
    あ
    1.22
     horrifying
    1.19
     kang
    1.17
     فى
    1.16
     대해서
    1.16
     ሊ
    1.14
    惻
    1.14
     recommendation
    1.14
    POSITIVE LOGITS
     күзгү
    1.01
    glEnd
    1.01
    acrylate
    0.94
    isomer
    0.93
    铬
    0.90
    Converters
    0.90
     диск
    0.88
     elet
    0.87
    Meyer
    0.87
    eglasses
    0.86
    Activations Density 0.004%

    No Known Activations