© 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
    3. 40-GEMMASCOPE-2-RES-16K
    4. 9203
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags and syntax

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

    SVG path data and attributes

    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_40_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
    ").
    0.66
    ').
    0.57
    ”).
    0.56
    `).
    0.55
    )").
    0.55
    "):
    0.53
     ").
    0.50
    </u>
    0.49
    )")
    0.47
    </h2>
    0.46
    POSITIVE LOGITS
    '/>
    1.32
    <h3>
    1.30
     />
    1.27
    "/>
    1.27
    =""/>
    1.26
    }/>
    1.23
    }"/>
    1.20
    )}/>
    1.15
     />;
    1.13
     />,
    1.08
    Activations Density 0.055%

    No Known Activations