© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 864
    Prev
    Next
    INDEX
    Explanations

    listing followed by closing parenthesis

    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
    </h3>
    3.02
    <h4>
    2.99
    </h5>
    2.96
    </h4>
    2.79
    </blockquote>
    2.72
    <h5>
    2.57
    <h3>
    2.49
    <h6>
    1.95
    </td>
    1.90
    ."""
    1.82
    POSITIVE LOGITS
    )
    5.92
    ),
    5.90
    ).
    5.43
    !)
    5.37
    ?)
    5.30
    )-
    5.21
    )،
    5.18
    ):
    5.17
    !),
    5.17
    ,)
    5.13
    Activations Density 2.594%

    No Known Activations