© 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. 251668
    Prev
    Next
    INDEX
    Explanations

    indemnify and hold harmless

    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
    lived
    0.47
    {{
    0.47
    sexy
    0.46
    nya
    0.46
    slug
    0.45
    asyonu
    0.45
    ash
    0.45
    ashed
    0.44
    {(
    0.44
    लित
    0.44
    POSITIVE LOGITS
    我们
    0.55
     пів
    0.52
    嫒
    0.48
    挚
    0.46
     Nadine
    0.46
     AVR
    0.46
    滟
    0.45
     án
    0.45
     Howe
    0.45
     שלה
    0.44
    Activations Density 0.001%

    No Known Activations