© 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. 110720
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    Anatom
    -0.85
    dì
    -0.75
     Prefeitura
    -0.74
     €)
    -0.73
    Tumblr
    -0.73
     vroeger
    -0.73
    werkers
    -0.71
    Gia
    -0.71
    |^{
    -0.71
    Ili
    -0.71
    POSITIVE LOGITS
     материалам
    0.94
     also
    0.92
    Lever
    0.92
     μία
    0.91
     unimaginable
    0.89
     potrebbe
    0.84
     myös
    0.84
     Morin
    0.82
    وم
    0.82
    continue
    0.80
    Activations Density 0.005%

    No Known Activations