© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91519
    Prev
    Next
    INDEX
    Explanations

    programming language components

    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
    ().
    -1.25
     also
    -1.21
     from
    -1.13
     pihaknya
    -1.09
     Также
    -1.09
     Y
    -1.06
     as
    -1.05
     according
    -1.05
     modestly
    -1.05
     L
    -1.02
    POSITIVE LOGITS
    ;
    
    1.30
    ;
    1.30
    ;</
    1.17
    </td>
    1.13
    føring
    1.09
     tilby
    1.08
     kılıf
    1.07
     ";
    
    1.07
     manicura
    1.07
    };
    1.05
    Activations Density 0.025%

    No Known Activations