© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14027
    Prev
    Next
    INDEX
    Explanations

    Language

    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_7_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
     предоставля
    1.75
    ย
    1.69
    PECT
    1.65
     Canadá
    1.60
     CANADA
    1.60
    ┃
    1.56
     principales
    1.56
     слід
    1.56
    確
    1.55
    మన్
    1.54
    POSITIVE LOGITS
    ek
    1.82
    chromium
    1.69
    efi
    1.59
    heus
    1.53
    egen
    1.52
    zeppelin
    1.51
    bart
    1.50
    toned
    1.45
    ʃ
    1.44
     horrendous
    1.44
    Activations Density 0.000%

    No Known Activations