© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13866
    Prev
    Next
    INDEX
    Explanations

    file paths and line numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    Vacancy
    1.18
    updateConfirm
    1.12
     vacancy
    1.09
    <unused1691>
    1.08
    <unused1101>
    1.07
     Interment
    1.06
    thapi
    1.05
     missionary
    1.04
     interment
    1.04
    ⅓
    1.04
    POSITIVE LOGITS
    不
    0.69
    self
    0.66
    endo
    0.64
    是不
    0.61
    top
    0.60
     lain
    0.59
    ace
    0.58
    做
    0.58
     tle
    0.58
    很
    0.57
    Activations Density 0.002%

    No Known Activations