© 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. 2457
    Prev
    Next
    INDEX
    Explanations

    but except

    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
     elytris
    1.79
    geoType
    1.70
    <unused2090>
    1.63
     confertim
    1.62
    <unused1248>
    1.62
     longiore
    1.62
    <unused1237>
    1.60
    <unused905>
    1.59
    <unused298>
    1.57
    RENDITION
    1.56
    POSITIVE LOGITS
     Am
    1.27
     et
    1.24
     Sam
    1.22
     In
    1.21
     International
    1.20
     V
    1.19
     At
    1.19
     Law
    1.16
     Nav
    1.15
     Court
    1.15
    Activations Density 0.239%

    No Known Activations