© 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. 31270
    Prev
    Next
    INDEX
    Explanations

    a combination

    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
     ontwikkeling
    -0.85
    lepší
    -0.81
    الصفحه
    -0.81
    cích
    -0.78
    ोध
    -0.77
    mbrie
    -0.77
     dezelfde
    -0.77
    )</
    -0.76
    𝗠
    -0.75
    Each
    -0.74
    POSITIVE LOGITS
     combination
    7.69
    combination
    6.31
    Combination
    5.97
     combinations
    5.69
     Combination
    5.69
     combinación
    5.66
     combine
    5.66
     kombin
    5.53
     combined
    5.41
     Kombination
    5.31
    Activations Density 0.446%

    No Known Activations