© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6380
    Prev
    Next
    INDEX
    Explanations

    key-value pairs like age and city

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    。「
    1.69
    -‘
    1.65
    áticas
    1.54
    .
    1.53
    ：「
    1.45
     cookbooks
    1.44
     (‘
    1.42
     captioned
    1.40
     ‘
    1.40
    —“
    1.40
    POSITIVE LOGITS
     newVal
    1.73
     minValue
    1.63
     newValue
    1.55
     newState
    1.54
    TempValue
    1.54
     glic
    1.53
     offsetY
    1.49
     died
    1.48
    Sou
    1.46
     distX
    1.46
    Activations Density 0.003%

    No Known Activations