© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25594
    Prev
    Next
    INDEX
    Explanations

    modules and code definitions

    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
     Khartoum
    -0.84
    ObjectModel
    -0.77
    utica
    -0.76
    ℑ
    -0.75
     instilled
    -0.75
    ཏ
    -0.74
    OLIC
    -0.73
    性价比
    -0.73
     گوش
    -0.72
    relser
    -0.72
    POSITIVE LOGITS
    También
    0.90
    setters
    0.86
    pecies
    0.85
    ichè
    0.85
    enumii
    0.83
     ejecución
    0.82
     työn
    0.82
     yapmak
    0.81
    }";
    0.81
     también
    0.81
    Activations Density 0.017%

    No Known Activations