© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2683
    Prev
    Next
    INDEX
    Explanations

    We are given

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     robustness
    2.11
    zeichnis
    2.07
     mobilisation
    2.05
     集
    2.05
     organising
    2.04
     hadn
    2.03
     Newsletter
    2.02
    ほしい
    2.01
    InstanceOf
    2.01
    shoring
    2.01
    POSITIVE LOGITS
     *$
    0.78
     estacion
    0.75
     upstairs
    0.75
    celli
    0.75
    вець
    0.73
    etter
    0.73
    reif
    0.72
     downstairs
    0.72
    ensin
    0.69
    sthrough
    0.68
    Activations Density 0.315%

    No Known Activations