© 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. 79538
    Prev
    Next
    INDEX
    Explanations

    verbs followed by common completions

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

    This neuron responds to verbs that introduce or discuss understanding, explanation, or ability (e.g. see, understand, help, explain, use).

    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
    <bos>
    -1.47
     poder
    -1.44
    能在
    -1.37
     pouvoir
    -1.33
         
    -1.26
    ቍ
    -1.23
     poter
    -1.21
    ጐ
    -1.16
     ability
    -1.11
        
    -1.10
    POSITIVE LOGITS
    ('
    1.32
     sambil
    1.21
     be
    1.20
    ᴅ
    1.15
     senjata
    1.15
     namelijk
    1.14
    тся
    1.12
     páns
    1.11
     with
    1.10
     Beamten
    1.09
    Activations Density 0.192%

    No Known Activations