© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6023
    Prev
    Next
    INDEX
    Explanations

    grace, vast, anxiety, tide

    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_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
    ennzeichnet
    1.59
     dhamme
    1.56
     viennent
    1.41
    忓
    1.37
    مله
    1.37
    تص
    1.35
     terletak
    1.34
    बरी
    1.31
    锑
    1.30
    পুরে
    1.30
    POSITIVE LOGITS
    ंग्रे
    1.64
    stairs
    1.52
     Hill
    1.44
     Fitch
    1.39
     hill
    1.38
     Lo
    1.38
    Dare
    1.35
     Conduit
    1.35
    political
    1.34
     political
    1.34
    Activations Density 0.158%

    No Known Activations