© 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. 62815
    Prev
    Next
    INDEX
    Explanations

    enumeration lists

    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
    excellence
    -0.96
    myModal
    -0.94
     Mungkin
    -0.85
     endroits
    -0.81
     comarca
    -0.80
     možno
    -0.78
     テラス
    -0.78
    ffmpeg
    -0.77
    へ行
    -0.77
     Peut
    -0.76
    POSITIVE LOGITS
     i
    1.23
     ii
    1.15
    iii
    1.07
     iii
    1.05
    1.05
    ii
    0.99
         
    0.92
     iv
    0.87
    0.85
                 
    0.83
    Activations Density 0.010%

    No Known Activations