© 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. 7476
    Prev
    Next
    INDEX
    Explanations

    ":" followed by true

    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
     медве
    0.40
    ﺐ
    0.38
     shrouded
    0.37
    这些
    0.36
    ப்பொரு
    0.36
     तन
    0.36
     zdoby
    0.35
     shroud
    0.34
    典型的
    0.34
     змо
    0.34
    POSITIVE LOGITS
    false
    0.44
     đỏ
    0.43
     ignored
    0.41
     পরিত্যাগ
    0.40
     giúp
    0.39
    仅
    0.39
     ctrl
    0.38
     hanya
    0.38
     jika
    0.38
     اگر
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.