© 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. 81481
    Prev
    Next
    INDEX
    Explanations

    All about, one of, open game, Friday,

    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
    LAYOUT
    -0.82
    experiment
    -0.77
    versaries
    -0.77
    pendenti
    -0.75
     height
    -0.73
    简单
    -0.72
     ausgesch
    -0.71
    簡單
    -0.71
     microw
    -0.70
     umožňuje
    -0.70
    POSITIVE LOGITS
     acquis
    1.31
    chapters
    1.10
     Approximation
    1.06
     alignment
    0.99
    setProgress
    0.98
     Alignment
    0.98
     approximation
    0.96
    alignment
    0.96
    Alignment
    0.94
     chapters
    0.92
    Activations Density 0.010%

    No Known Activations