© 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. 110736
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    ErrorException
    -0.87
     média
    -0.84
    Źródło
    -0.82
    taient
    -0.81
    rosio
    -0.80
    وصلات
    -0.80
    cours
    -0.79
     beslut
    -0.79
     dientes
    -0.78
    føl
    -0.78
    POSITIVE LOGITS
     {@
    1.53
    }<
    1.04
     <
    0.98
     $<
    0.97
    {@
    0.96
     ${\
    0.89
     see
    0.87
    <sup>
    0.85
     If
    0.78
     It
    0.77
    Activations Density 0.016%

    No Known Activations