© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84617
    Prev
    Next
    INDEX
    Explanations

    free application process

    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
    מת
    -0.81
     infra
    -0.77
     Roller
    -0.74
    buena
    -0.74
    ]));
    -0.73
    فل
    -0.73
    رات
    -0.72
    MenuInflater
    -0.72
     Pole
    -0.69
    uanya
    -0.68
    POSITIVE LOGITS
     sale
    1.20
     selling
    1.20
     sold
    1.07
     sell
    1.00
    Selling
    0.97
     прода
    0.96
    sale
    0.94
     prescribe
    0.93
     sells
    0.92
     downloading
    0.91
    Activations Density 0.018%

    No Known Activations