© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 2332
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    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
    ↵
    3.51
    <start_of_image>
    2.15
    <h2>
    2.13
    </h2>
    2.01
    '',
    1.87
    】,
    1.86
    ’,
    1.79
    ”,
    1.78
    」、
    1.65
    \
    1.65
    POSITIVE LOGITS
    .")
    2.94
    ."]
    2.84
    .”)
    2.80
    。)
    2.70
    .]
    2.64
    ]."
    2.58
    </sub>
    2.56
    ].)
    2.51
    .'"
    2.51
    .])
    2.48
    Activations Density 0.290%

    No Known Activations