© 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. 34-GEMMASCOPE-RES-131K
    7. 92905
    Prev
    Next
    INDEX
    Explanations

    code endings );

    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_34/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
    ,
    -1.55
    */].
    -0.98
     etc
    -0.97
    mch
    -0.93
    pisah
    -0.93
     zanim
    -0.93
     ").
    -0.92
    っていない
    -0.91
    ิ่ง
    -0.90
    (),
    -0.90
    POSITIVE LOGITS
    <h3>
    1.12
     Bretaña
    1.10
    . 
    1.09
    的她
    1.09
    tronlink
    1.05
    Ꝑ
    1.00
     Bayard
    1.00
    īj
    1.00
    Interment
    1.00
    新浪
    0.99
    Activations Density 0.033%

    No Known Activations