© 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. 87154
    Prev
    Next
    INDEX
    Explanations

    code identifiers and 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
    mth
    -0.93
    cinogenicity
    -0.87
    contentView
    -0.87
     bölüm
    -0.86
     doby
    -0.84
     Mum
    -0.83
    <mask>
    -0.81
    DidLoad
    -0.80
    <blockquote>
    -0.80
    inę
    -0.80
    POSITIVE LOGITS
     huf
    0.95
     udang
    0.95
     volete
    0.87
     dicono
    0.86
     marinho
    0.86
     vogliono
    0.85
     fotografico
    0.85
    皝
    0.84
    jamientos
    0.84
     yama
    0.84
    Activations Density 0.009%

    No Known Activations