© 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. 3268
    Prev
    Next
    INDEX
    Explanations

    checking response status or text

    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
    jonal
    0.96
    逮
    0.94
     Nemours
    0.92
    zków
    0.90
     campa
    0.82
     ninguno
    0.82
    raisers
    0.81
    ):["
    0.80
    ándor
    0.80
    lion
    0.79
    POSITIVE LOGITS
     Alla
    1.42
     Misty
    1.40
     znamená
    1.33
     Aka
    1.32
     Spes
    1.32
     Warp
    1.30
     Dharma
    1.30
     Myst
    1.29
    arankan
    1.29
     Spirit
    1.26
    Activations Density 0.076%

    No Known Activations