© 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. 986
    Prev
    Next
    INDEX
    Explanations

    /

    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
     K
    1.60
     D
    1.54
    1.50
     M
    1.50
     T
    1.49
     L
    1.47
     P
    1.44
     B
    1.42
     C
    1.41
     J
    1.38
    POSITIVE LOGITS
     elytris
    1.93
    <unused1237>
    1.92
    <unused298>
    1.88
    <unused2090>
    1.85
    <unused1261>
    1.83
     confertim
    1.80
    <unused820>
    1.79
    <unused1252>
    1.79
    <unused817>
    1.78
    <unused138>
    1.77
    Activations Density 0.420%

    No Known Activations