© 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. 14839
    Prev
    Next
    INDEX
    Explanations

    locations, subjects, or code targets

    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
     setSnackbar
    2.01
     thumbnailUrl
    2.01
     artistdata
    2.01
     titleImageUrl
    2.01
    édi
    2.00
    <unused1204>
    1.94
    亽
    1.94
    <unused1939>
    1.93
     fB
    1.92
    <unused1243>
    1.90
    POSITIVE LOGITS
    a
    1.76
     recuerda
    1.60
    perfect
    1.55
     Kail
    1.51
     perfect
    1.44
    हारी
    1.42
    ২৯
    1.42
    ৩৩
    1.40
    k
    1.39
     G
    1.38
    Activations Density 0.000%

    No Known Activations