© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84763
    Prev
    Next
    INDEX
    Explanations

    Josh names

    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
     lad
    -0.84
     trait
    -0.83
    ardu
    -0.77
     dae
    -0.75
    輿
    -0.72
     thermo
    -0.70
     duidelijk
    -0.70
     staging
    -0.70
    ],"
    -0.69
     Ι
    -0.67
    POSITIVE LOGITS
     venir
    0.84
     Discuss
    0.77
     avantaj
    0.75
    きら
    0.75
     différente
    0.75
    ukų
    0.74
    tagens
    0.74
    iotto
    0.73
    หย
    0.73
     titulares
    0.73
    Activations Density 0.028%

    No Known Activations