© 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. 94133
    Prev
    Next
    INDEX
    Explanations

    json schema

    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
    gene
    -0.96
     They
    -0.91
    就算是
    -0.91
    Nau
    -0.88
     HTML
    -0.88
    akkan
    -0.87
    たちは
    -0.86
    deacon
    -0.86
     elo
    -0.85
    态度
    -0.83
    POSITIVE LOGITS
    rpc
    1.25
    bject
    1.01
    esque
    1.01
    epresidente
    0.95
    object
    0.95
     ועל
    0.91
     strict
    0.91
     purification
    0.90
    ification
    0.89
    oluble
    0.88
    Activations Density 0.030%

    No Known Activations