© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1298
    Prev
    Next
    INDEX
    Explanations

    woven with threads

    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_65k_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
    ,
    0.99
    ruari
    0.93
    R
    0.92
    ของ
    0.92
    .
    0.90
    eur
    0.84
     của
    0.83
    itoria
    0.82
     and
    0.82
     il
    0.82
    POSITIVE LOGITS
    <unused1834>
    1.58
    <unused967>
    1.54
    <unused302>
    1.50
    ვით
    1.48
    mobilpay
    1.47
    <unused969>
    1.47
     মহাশয়
    1.44
    <unused758>
    1.42
    ον
    1.42
    <unused989>
    1.41
    Activations Density 0.805%

    No Known Activations