© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6109
    Prev
    Next
    INDEX
    Explanations

    recalling specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    es
    1.14
    ed
    1.07
    ar
    1.04
    room
    1.02
    ec
    0.95
    ру
    0.93
    i
    0.92
    arap
    0.91
    esis
    0.91
     có
    0.89
    POSITIVE LOGITS
     Publikum
    1.72
    Loksatta
    1.72
    ឪ
    1.69
    ꔰ
    1.66
     Narayan
    1.64
     Draper
    1.64
    Turner
    1.63
     vectorstock
    1.62
    Roche
    1.62
    <unused366>
    1.61
    Activations Density 0.000%

    No Known Activations