© 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. 49947
    Prev
    Next
    INDEX
    Explanations

    C/C++ code with pointers

    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
    Tutto
    -0.83
     esconde
    -0.82
    Ecco
    -0.81
    拿到
    -0.81
     ratusan
    -0.80
    Interess
    -0.79
     beſ
    -0.76
    Everything
    -0.74
     alkot
    -0.74
    weh
    -0.74
    POSITIVE LOGITS
    ptr
    0.91
     resulta
    0.91
     reta
    0.80
    ͮ
    0.77
    (__
    0.76
     Rector
    0.76
    pirable
    0.74
     (__
    0.72
    ventude
    0.72
     Hardin
    0.71
    Activations Density 0.001%

    No Known Activations