© 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. 3595
    Prev
    Next
    INDEX
    Explanations

    lists followed by explanations

    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
     principalmente
    1.39
     buscar
    1.36
    '+
    1.25
     deswegen
    1.24
    🔸
    1.22
    時候
    1.21
     karna
    1.20
    ﹑
    1.19
     namelijk
    1.18
    這邊
    1.16
    POSITIVE LOGITS
     favorably
    2.04
     Remarkably
    1.95
     Voilà
    1.92
     admirably
    1.89
     laud
    1.88
     replete
    1.85
    ahre
    1.83
    ​—
    1.82
     Evidently
    1.82
     strikingly
    1.82
    Activations Density 0.217%

    No Known Activations