© 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. 1868
    Prev
    Next
    INDEX
    Explanations

    components, characteristics, structures

    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
     właścic
    1.74
     boulders
    1.67
     歩
    1.62
    蜊
    1.62
     Gravel
    1.61
     saque
    1.58
     現
    1.58
     پت
    1.56
     Stel
    1.56
     strontium
    1.56
    POSITIVE LOGITS
    ably
    1.89
    tie
    1.84
    t
    1.73
    inflammatory
    1.70
    ermost
    1.69
    able
    1.68
    tis
    1.63
    tied
    1.60
    fitted
    1.59
    twe
    1.59
    Activations Density 0.152%

    No Known Activations