© 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. 98896
    Prev
    Next
    INDEX
    Explanations

    aimed at, key step

    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
     others
    -0.80
     While
    -0.77
     efficiently
    -0.73
     those
    -0.73
     their
    -0.73
     can
    -0.72
     while
    -0.72
    しつつ
    -0.71
     could
    -0.70
     develop
    -0.70
    POSITIVE LOGITS
     elseif
    0.95
    hibition
    0.95
     Hind
    0.92
     пожела
    0.86
    Hind
    0.84
    orite
    0.81
    ioren
    0.81
    ᠵ
    0.81
    atars
    0.79
    лением
    0.79
    Activations Density 0.036%

    No Known Activations