© 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. 10-GEMMASCOPE-RES-131K
    7. 104316
    Prev
    Next
    INDEX
    Explanations

    lead to consequences

    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_10/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
    Ꮨ
    -1.66
     ibland
    -1.63
     galaxia
    -1.55
     nästan
    -1.54
     snabbt
    -1.52
    ום
    -1.51
     kohdetta
    -1.51
     quelquefois
    -1.49
     debía
    -1.45
    לים
    -1.44
    POSITIVE LOGITS
     be
    2.64
     if
    2.08
     soon
    1.91
    {
    1.47
     some
    1.44
     –
    1.44
    "
    1.41
     continue
    1.41
     you
    1.40
     later
    1.38
    Activations Density 1.884%

    No Known Activations