© 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. 58516
    Prev
    Next
    INDEX
    Explanations

    code or technical documentation markers

    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
    ----+
    -1.04
    ង
    -0.93
     brune
    -0.90
    Ḩ
    -0.88
     carcasa
    -0.88
     gerekiyor
    -0.88
    龛
    -0.86
     idly
    -0.86
     multicolore
    -0.85
    不断的
    -0.84
    POSITIVE LOGITS
    пать
    0.88
     Nig
    0.86
     
    0.86
     ’
    0.85
    contentView
    0.85
     Obwohl
    0.84
                        
    0.84
     Password
    0.84
     Survey
    0.83
     Snapchat
    0.82
    Activations Density 0.005%

    No Known Activations