© 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. 87028
    Prev
    Next
    INDEX
    Explanations

    Eleven

    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
    Bs
    -0.85
     مد
    -0.82
    нё
    -0.81
    ⡀
    -0.79
     Dars
    -0.77
     Als
    -0.75
    াস
    -0.73
     Лин
    -0.73
    modb
    -0.72
    Gone
    -0.71
    POSITIVE LOGITS
     Eleven
    0.80
    アフリカ
    0.75
     Eleventh
    0.73
     harassed
    0.71
    Pkt
    0.69
    liable
    0.69
     Limiting
    0.69
     invariable
    0.66
    Eleven
    0.65
     pagoda
    0.65
    Activations Density 0.517%

    No Known Activations