© 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. 65926
    Prev
    Next
    INDEX
    Explanations

    self-orthogonal, New Species, unlawful possession

    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
     žen
    -0.80
    扳
    -0.77
    Ⓡ
    -0.77
    Gabri
    -0.76
    udis
    -0.74
     Chances
    -0.73
     високо
    -0.70
    Blitz
    -0.69
     deta
    -0.68
     batch
    -0.68
    POSITIVE LOGITS
    neq
    0.90
     eq
    0.89
    otropy
    0.87
    Le
    0.87
    μερα
    0.84
    Your
    0.83
    oría
    0.82
    fighters
    0.82
    cancel
    0.81
    два
    0.81
    Activations Density 0.006%

    No Known Activations