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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13006
    Prev
    Next
    INDEX
    Explanations

    What brings you

    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
    acceptable
    1.02
    endpoint
    0.99
     incapac
    0.98
    ぼ
    0.97
     extraneous
    0.96
    minim
    0.95
     outfile
    0.95
     frivolous
    0.94
    paysys
    0.94
     stumpage
    0.94
    POSITIVE LOGITS
    ’
    1.13
    '
    1.12
     has
    0.97
    ulla
    0.96
     topped
    0.94
     went
    0.91
     বেগ
    0.88
    uje
    0.88
     terdiri
    0.88
    یت
    0.88
    Activations Density 0.019%

    No Known Activations