© 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. 4364
    Prev
    Next
    INDEX
    Explanations

    You can use

    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
    ereo
    1.52
     permissive
    1.48
     ours
    1.48
     cameras
    1.47
     clearances
    1.47
    agena
    1.44
    ."],
    1.42
     adjuster
    1.42
     graced
    1.42
     jamming
    1.42
    POSITIVE LOGITS
     biết
    1.29
    明白
    1.25
     Martínez
    1.17
     kub
    1.17
     Navarre
    1.11
     ног
    1.10
     déclar
    1.09
     Seiten
    1.09
    Literal
    1.09
    淚
    1.05
    Activations Density 0.020%

    No Known Activations