© 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. 40123
    Prev
    Next
    INDEX
    Explanations

    risks and their consequences

    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
     
    -3.03
    The
    -2.63
        
    -2.41
     For
    -2.28
    <td>
    -2.25
                
    -2.22
     “
    -2.14
     \
    -2.11
    <blockquote>
    -2.06
     The
    -2.03
    POSITIVE LOGITS
    鲼
    2.70
    釹
    2.69
     ,‬
    2.64
     destes
    2.64
    s
    2.47
    饪
    2.42
    镡
    2.39
    
    2.34
    檬
    2.28
    μαστε
    2.27
    Activations Density 0.004%

    No Known Activations