© 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. 33239
    Prev
    Next
    INDEX
    Explanations

    SHA512 hashes

    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
    ostante
    -0.94
    Freund
    -0.91
     адрес
    -0.84
    Holz
    -0.84
    Gemeinsame
    -0.83
    Alternative
    -0.83
     škoda
    -0.82
     себя
    -0.80
     niedrig
    -0.80
    让他们
    -0.79
    POSITIVE LOGITS
     algum
    0.82
     Segen
    0.82
     whats
    0.76
    }>
    
    0.75
    流
    0.74
    !
    0.74
    DispatchToProps
    0.73
     Jum
    0.73
    cinations
    0.73
    DESCRIPTOR
    0.73
    Activations Density 0.036%

    No Known Activations