© 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. 79169
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and conditions

    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
    庚
    -0.91
     Saturday
    -0.90
    ⑥
    -0.83
    ⑦
    -0.79
     heels
    -0.79
     Seventh
    -0.77
    ắ
    -0.75
    ponym
    -0.75
     muerta
    -0.74
    inkler
    -0.74
    POSITIVE LOGITS
         
    1.58
                 
    1.27
             
    1.27
                         
    1.02
                     
    0.94
    óf
    0.86
                                 
    0.85
    ốn
    0.82
    enciado
    0.81
    <0xB4>
    0.80
    Activations Density 0.064%

    No Known Activations