© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93871
    Prev
    Next
    INDEX
    Explanations

    statements of assumption

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

    The neuron is primarily triggered by the word “guide” (especially in section or document titles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     McManus
    -0.81
     faktiskt
    -0.75
     jalan
    -0.74
    俏
    -0.73
    Andrzej
    -0.73
    AfterClass
    -0.73
    coledì
    -0.71
    언
    -0.70
    Exeunt
    -0.70
    nesty
    -0.70
    POSITIVE LOGITS
     assume
    6.22
     assuming
    5.94
     assumes
    5.81
     assumed
    5.78
     assumption
    5.78
    assume
    5.38
    assuming
    5.13
     Assume
    5.09
    Assume
    5.09
     assumptions
    4.97
    Activations Density 0.187%

    No Known Activations