© 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. 37344
    Prev
    Next
    INDEX
    Explanations

    Nephilim, giants, fallen angels

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

    stack, bytecode

    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
    虏
    0.42
     Optical
    0.40
     Ahmed
    0.39
    हारिक
    0.39
     Medicina
    0.38
     officia
    0.38
    瀕
    0.38
     साधा
    0.38
    蝰
    0.38
     कहला
    0.38
    POSITIVE LOGITS
    Tower
    0.43
    tower
    0.43
     babel
    0.42
    byteArray
    0.41
    stack
    0.41
    Visiting
    0.40
     Babylon
    0.40
     tower
    0.39
    visitor
    0.39
    post
    0.38
    Activations Density 0.018%

    No Known Activations