© 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. 89714
    Prev
    Next
    INDEX
    Explanations

    cave diving and Tap Dogs

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

    endoscopic, clinoptilolite, API, kids

    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
    ולנדי
    0.49
    एगी
    0.48
     sprawl
    0.48
    ดวก
    0.46
    ن
    0.46
     سبب
    0.45
    נדי
    0.45
    ectady
    0.45
    GH
    0.45
     comparability
    0.45
    POSITIVE LOGITS
     músicas
    0.44
     ressent
    0.44
     Đá
    0.43
    '
    0.43
    뻣
    0.42
     totales
    0.42
     integración
    0.42
     össz
    0.41
     potência
    0.41
    続け
    0.41
    Activations Density 0.001%

    No Known Activations