© 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. 777
    Prev
    Next
    INDEX
    Explanations

    archaic spellings and historical name mentions

    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
     zemi
    -1.01
     fémin
    -0.96
    diese
    -0.93
     transparentes
    -0.90
     فيلم
    -0.88
    Corey
    -0.88
     solides
    -0.88
     esposo
    -0.87
    zoeken
    -0.87
    申请
    -0.86
    POSITIVE LOGITS
    MMdd
    0.96
    ly
    0.90
     keiner
    0.89
    ys
    0.86
     horrible
    0.86
     Ys
    0.85
     hefyd
    0.85
    yers
    0.84
    Y
    0.84
    y
    0.83
    Activations Density 0.016%

    No Known Activations