© 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. 4182
    Prev
    Next
    INDEX
    Explanations

    doorstep delivery

    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
    ار
    0.68
    يد
    0.68
    ру
    0.65
    ليل
    0.62
    _
    0.61
    자
    0.61
    كل
    0.60
    }",
    0.60
    ۲
    0.59
    عية
    0.58
    POSITIVE LOGITS
     doorstep
    0.93
    k
    0.71
     doorbell
    0.70
    ก
    0.68
    5
    0.64
     home
    0.63
     door
    0.62
     address
    0.61
    medicine
    0.61
     threshold
    0.61
    Activations Density 0.003%

    No Known Activations