© 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. 22-GEMMASCOPE-RES-131K
    7. 70378
    Prev
    Next
    INDEX
    Explanations

    I'm sure followed by belief

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on hedge/introductory phrases expressing assumed shared perspective—especially the “I’m sure that you…” construction.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Perhaps
    -1.55
     perhaps
    -1.48
     faktiskt
    -1.38
    訇
    -1.34
     Recently
    -1.34
    Perhaps
    -1.30
     ועל
    -1.28
     Possibly
    -1.27
     actually
    -1.26
    ()]
    -1.26
    POSITIVE LOGITS
     many
    1.42
    ,
    1.30
     will
    1.16
     
    1.12
     plenty
    1.10
    many
    1.10
     vieler
    1.10
     wielu
    1.09
    some
    1.07
     SOME
    1.02
    Activations Density 0.013%

    No Known Activations