© 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. 1563
    Prev
    Next
    INDEX
    Explanations

    public key

    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
     Tx
    1.04
    Tx
    1.04
     Tj
    1.02
     Tsch
    1.02
     Tym
    0.97
     Th
    0.92
    wia
    0.92
     T
    0.91
    滕
    0.91
    x
    0.89
    POSITIVE LOGITS
    Sets
    1.10
    ASSOC
    1.07
    sets
    1.07
    Set
    1.07
    apuris
    1.06
     sets
    1.04
     set
    1.03
    Benchmarks
    1.00
    SETS
    0.99
     Set
    0.98
    Activations Density 0.519%

    No Known Activations