© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22142
    Prev
    Next
    INDEX
    Explanations

    ongoing + continuing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <
    -2.39
     The
    -2.36
    几
    -2.17
     ก็
    -2.14
    </h1>
    -2.11
     όταν
    -2.11
     director
    -2.09
    </td>
    -2.09
    </i>
    -2.08
    </b>
    -2.03
    POSITIVE LOGITS
    짙
    2.55
    ⛦
    2.39
    蜑
    2.39
    媖
    2.19
    
    2.19
    n
    2.14
     hodiny
    2.11
    ……”
    2.11
    
    2.11
    ☫
    2.08
    Activations Density 0.006%

    No Known Activations