© 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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 16505
    Prev
    Next
    INDEX
    Explanations

    checking items or understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h2>
    0.97
    ')
    0.76
    '));
    0.76
    s
    0.70
    </h4>
    0.68
    });
    0.68
    </u>
    0.68
    رير
    0.67
    <0x0D>
    0.66
    ]");
    0.65
    POSITIVE LOGITS
    il
    0.82
     Checking
    0.79
     checking
    0.77
    é
    0.71
    do
    0.71
    ul
    0.70
    Checking
    0.70
    та
    0.68
     Checked
    0.66
    is
    0.65
    Activations Density 0.006%

    No Known Activations