© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164045
    Prev
    Next
    INDEX
    Explanations

    microscopic valleys

    np_acts-logits-general · gemini-2.5-flash-lite

    her heart | bodies | lineage of | debate | special

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    缓
    0.50
    for
    0.48
     superseded
    0.47
    ارم
    0.46
     reaff
    0.45
     obed
    0.45
     fg
    0.44
     푸
    0.44
    selen
    0.44
    app
    0.42
    POSITIVE LOGITS
    ják
    0.52
     wichtigsten
    0.49
     सर्किट
    0.48
     ಜೊ
    0.48
    Qualification
    0.46
    ंसह
    0.46
    }*/
    0.45
     Chakrab
    0.45
     fontos
    0.45
    Ę
    0.45
    Activations Density 0.000%

    No Known Activations