© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 864
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    </h3>
    1.42
     '
    1.24
     «
    1.16
     {@
    1.12
    </th>
    0.96
    </h5>
    0.95
    </span>
    0.95
     ('
    0.94
    </u>
    0.87
     )}
    0.86
    POSITIVE LOGITS
    ”
    5.48
    ”.
    4.85
    ”,
    4.77
    ”-
    4.58
    ”:
    4.58
    ”;
    4.50
    ”(
    4.49
    ”!
    4.41
    ”…
    4.35
    ”،
    4.33
    Activations Density 1.421%

    No Known Activations