© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4342
    Prev
    Next
    INDEX
    Explanations

    specific items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    ways or methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    <0xC2>
    0.62
    })$.
    0.59
    ).\
    0.59
    .'),
    0.59
    .');
    0.55
    })$;
    0.55
    $.;
    0.53
    .").
    0.53
    .).
    0.51
    ."),
    0.50
    POSITIVE LOGITS
    </h3>
    1.43
    </h2>
    1.38
    </h4>
    1.37
    </h5>
    1.14
    </h1>
    0.97
    </h6>
    0.92
    </b>
    0.75
    Permalink
    0.64
    </u>
    0.64
    ‬
    0.64
    Activations Density 0.091%

    No Known Activations