© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 105850
    Prev
    Next
    INDEX
    Explanations

    web crawling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    svelte
    0.68
    сред
    0.64
    también
    0.64
    skih
    0.63
    sonic
    0.59
    cep
    0.59
    ۹
    0.59
    ས་
    0.57
    cuenta
    0.57
    telefono
    0.57
    POSITIVE LOGITS
     odor
    0.59
     behavioral
    0.57
     foreclosure
    0.57
     prohibitive
    0.57
     dotyczące
    0.57
     exhilarating
    0.57
     dla
    0.56
     to
    0.55
     harness
    0.55
     invaluable
    0.55
    Activations Density 0.024%

    No Known Activations