© 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. 5329
    Prev
    Next
    INDEX
    Explanations

    discussion or debate

    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
     (“
    2.28
     “
    2.10
    (“
    2.06
    “
    2.02
     “(
    1.98
    .”
    1.94
    .”—
    1.91
    ”
    1.91
     „
    1.85
     („
    1.84
    POSITIVE LOGITS
    PhysRev
    1.45
     discusión
    1.34
    Millis
    1.32
    }],
    1.30
     Chakraborty
    1.29
     Sarkar
    1.29
    )]{
    1.28
    }),
    1.26
    KAK
    1.26
    chern
    1.24
    Activations Density 0.010%

    No Known Activations