© 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. 80969
    Prev
    Next
    INDEX
    Explanations

    assume or think

    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
    了出去
    -0.92
     forse
    -0.92
    んだり
    -0.89
     armon
    -0.82
     vägen
    -0.81
    òi
    -0.80
     exces
    -0.79
    ょう
    -0.79
    fal
    -0.79
    也可以
    -0.77
    POSITIVE LOGITS
     think
    3.80
     assume
    3.16
     assumes
    2.88
     thinks
    2.84
    以为
    2.78
    以為
    2.75
     assumption
    2.73
     believe
    2.73
    认为
    2.67
     assumed
    2.56
    Activations Density 0.100%

    No Known Activations