© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 952
    Prev
    Next
    INDEX
    Explanations

    surname requests and outputs

    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_65k_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
     RasterModelGrid
    0.97
     BlueprintName
    0.93
     Komponenten
    0.90
     HTMLSc
    0.90
    <unused893>
    0.87
    LOTREntity
    0.87
    𝘻
    0.87
     registrazione
    0.85
     GoObject
    0.84
     trataro
    0.83
    POSITIVE LOGITS
    <0xC2>
    1.05
    <0x0D>
    0.96
    ophysical
    0.94
    ­
    0.91
    xiety
    0.87
    ocortic
    0.84
    ë
    0.84
    ief
    0.84
    agem
    0.83
    omio
    0.82
    Activations Density 8.308%

    No Known Activations