© 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. 110220
    Prev
    Next
    INDEX
    Explanations

    words following "Board", "network", "how", "category", "our"

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

    from delaying

    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
    த்தட்ட
    0.47
    ”-
    0.46
    演出
    0.45
    .’’
    0.43
     Rocks
    0.42
    RequestId
    0.42
     petit
    0.41
     ঘুষ
    0.41
     Тол
    0.41
    演唱
    0.41
    POSITIVE LOGITS
     FIND
    0.44
    
    0.43
    🗺
    0.43
    ُمْ
    0.43
    דינה
    0.43
    тук
    0.42
    लिख
    0.42
     aeronaut
    0.42
    turquoise
    0.41
    під
    0.41
    Activations Density 0.000%

    No Known Activations