© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3668
    Prev
    Next
    INDEX
    Explanations

    exception handling

    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
     موجب
    1.45
    ]',
    1.40
     ![](
    1.40
    }.")
    1.28
     injurious
    1.28
    后期
    1.25
    ++',
    1.22
    すすめ
    1.22
    不如
    1.21
    ]",
    1.20
    POSITIVE LOGITS
     homogeneity
    0.96
    creen
    0.95
    ifik
    0.94
     screens
    0.88
     impartiality
    0.85
     screen
    0.85
    ugas
    0.83
    aing
    0.83
    Facts
    0.82
    ôtel
    0.82
    Activations Density 0.082%

    No Known Activations