© 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. 105433
    Prev
    Next
    INDEX
    Explanations

    templates and account

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

    apple yellow

    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
     handbag
    0.47
     pods
    0.46
     unstructured
    0.46
    了大
    0.41
     fractions
    0.40
     কিছুক্ষণ
    0.40
    unittest
    0.40
    ]}
    0.39
    大家好
    0.39
    beh
    0.39
    POSITIVE LOGITS
     यामध्ये
    0.57
     கிராம்
    0.49
    inhard
    0.47
    Succ
    0.46
    IVEN
    0.46
    Strategy
    0.45
     معیار
    0.45
    Logic
    0.45
     बदलते
    0.45
     सुरेंद्र
    0.45
    Activations Density 0.000%

    No Known Activations