© 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-65K
    4. 2400
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and entities

    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
    В
    1.06
    of
    1.02
    ofthe
    0.97
    <strong>
    0.87
    and
    0.84
    ofs
    0.80
    no
    0.79
    from
    0.79
    atop
    0.78
    ov
    0.77
    POSITIVE LOGITS
     menimbulkan
    1.38
     hadir
    1.36
     muncul
    1.33
     danza
    1.29
    𐰣
    1.29
     príncipe
    1.28
     îles
    1.27
     démont
    1.27
    <unused1696>
    1.26
     pasó
    1.26
    Activations Density 0.039%

    No Known Activations