© 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. 166020
    Prev
    Next
    INDEX
    Explanations

    early model or Seed Oil

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

    descriptive terms followed by related nouns

    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
    हर
    0.46
    不动
    0.46
    🛖
    0.46
     Architecture
    0.45
     ceremonies
    0.44
    Architecture
    0.44
    依然
    0.43
     cuisines
    0.43
     Architectural
    0.42
    感动
    0.42
    POSITIVE LOGITS
    deviceID
    0.46
    worker
    0.45
     சேர்த்த
    0.45
    
    0.43
    কর্মী
    0.43
     فرض
    0.42
    ռ
    0.42
     syphilit
    0.42
    現實
    0.42
     معاش
    0.41
    Activations Density 0.000%

    No Known Activations