© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 8407
    Prev
    Next
    INDEX
    Explanations

    shape dimensions

    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
    /
    1.18
     /
    1.16
    -
    1.13
    ↵
    1.06
     (
    1.06
    <em>
    1.03
     |
    1.02
    <strong>
    0.98
    es
    0.98
    .
    0.97
    POSITIVE LOGITS
     avión
    1.60
    <unused1493>
    1.58
    𒀫
    1.57
    Ⴖ
    1.56
     रोजिक
    1.55
    𒀯
    1.53
    <unused1333>
    1.52
    ্ঞ
    1.52
     SIINFE
    1.52
    DeferredGroup
    1.52
    Activations Density 0.007%

    No Known Activations