© 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. 116869
    Prev
    Next
    INDEX
    Explanations

    future certainty or intention

    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
     telah
    -1.07
    来歴
    -1.05
     đã
    -1.02
     occas
    -0.96
     особенно
    -0.92
    已經
    -0.91
     نے
    -0.90
    érés
    -0.90
     memili
    -0.90
     иногда
    -0.89
    POSITIVE LOGITS
     gonna
    1.91
     be
    1.84
     surely
    1.76
     definitely
    1.45
     able
    1.41
     sicuramente
    1.31
     like
    1.23
     soon
    1.22
     not
    1.17
     certainly
    1.17
    Activations Density 0.035%

    No Known Activations