© 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. 92491
    Prev
    Next
    INDEX
    Explanations

    in the form

    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
    fizierung
    -0.84
     saisons
    -0.76
     mediocre
    -0.75
    usters
    -0.72
     sibling
    -0.72
    境的
    -0.72
    ल्क
    -0.71
     goodness
    -0.71
     conteúdo
    -0.70
    rivial
    -0.70
    POSITIVE LOGITS
     standard
    0.99
     factored
    0.91
     expanded
    0.88
     compact
    0.88
    ⠐
    0.84
     vectorial
    0.82
     Cartesian
    0.79
     tabular
    0.79
     compacted
    0.77
    هات
    0.77
    Activations Density 0.066%

    No Known Activations