© 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. 33646
    Prev
    Next
    INDEX
    Explanations

    descriptors followed by specific items

    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
     място
    -0.96
     disprove
    -0.94
    ikkert
    -0.94
    Skal
    -0.91
    PENUTUP
    -0.91
     recém
    -0.90
    可爱的
    -0.90
    Prosec
    -0.90
    gewiesen
    -0.90
     zweck
    -0.89
    POSITIVE LOGITS
    īb
    0.91
     mount
    0.88
     starts
    0.84
    气候
    0.84
    ?";
    0.83
     There
    0.83
    istream
    0.82
    tbody
    0.82
     does
    0.81
     ACTION
    0.79
    Activations Density 0.100%

    No Known Activations