© 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. 106939
    Prev
    Next
    INDEX
    Explanations

    legal, code, and foreign words

    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
     Replace
    -0.84
     DELETE
    -0.84
     limpi
    -0.83
    Creating
    -0.80
     reclaimed
    -0.79
     измени
    -0.79
    playmobil
    -0.77
    自己是
    -0.77
    seguir
    -0.76
     умень
    -0.76
    POSITIVE LOGITS
     чувства
    0.85
     unnecessarily
    0.83
     după
    0.83
    DEPARTMENT
    0.80
    悻
    0.80
    加以
    0.79
    નું
    0.78
    ko
    0.78
     cliquant
    0.77
    被
    0.77
    Activations Density 0.346%

    No Known Activations