© 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. 188600
    Prev
    Next
    INDEX
    Explanations

    elastic strap, professional clean, documenting injury

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

    metastatic cancer and features

    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
    ophages
    0.47
     ऑन
    0.46
    punkt
    0.44
    躇
    0.44
    ੲ
    0.44
    onomous
    0.44
    यह
    0.43
    freie
    0.43
    ఈ
    0.43
    import
    0.43
    POSITIVE LOGITS
     neve
    0.50
     vro
    0.50
     hielo
    0.50
     petroleum
    0.48
     prawn
    0.47
    n
    0.46
     さ
    0.46
     '_
    0.44
     Tough
    0.43
     lũ
    0.43
    Activations Density 0.001%

    No Known Activations