© 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. 2349
    Prev
    Next
    INDEX
    Explanations

    json format output

    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
    𒌆
    2.55
    <unused12>
    2.45
    Methylsulfanyl
    2.44
     UWGM
    2.42
     payog
    2.42
    <unused1203>
    2.40
    <unused1276>
    2.38
     paździer
    2.38
    𒂍
    2.37
    <unused1382>
    2.35
    POSITIVE LOGITS
     of
    1.73
    at
    1.64
    ,
    1.49
    in
    1.46
    acing
    1.41
    ar
    1.36
    out
    1.35
    ac
    1.34
     in
    1.32
    per
    1.32
    Activations Density 0.179%

    No Known Activations