© 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. 115970
    Prev
    Next
    INDEX
    Explanations

    religious and mythological figures

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

    in New Jersey

    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
     மிகப்பெ
    0.53
     స్థాయిలో
    0.48
    惊
    0.47
     அம்பேத்கர்
    0.47
     लिहाज
    0.47
     статисти
    0.47
    PolicyQuery
    0.47
     риск
    0.46
    GBuf
    0.45
    慓
    0.45
    POSITIVE LOGITS
     auto
    0.48
    auto
    0.45
     polyurethane
    0.45
     capital
    0.42
     candies
    0.42
    capital
    0.42
     automobiles
    0.42
     money
    0.42
     korea
    0.41
     company
    0.41
    Activations Density 0.000%

    No Known Activations