© 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. 66076
    Prev
    Next
    INDEX
    Explanations

    impose or dictate rules

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

    The neuron responds in proportion to token length, strongly activating on longer words.

    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
    зыв
    -0.82
    rief
    -0.79
     consente
    -0.78
    ാ
    -0.78
    ernan
    -0.78
    &=&\
    -0.77
    drawSprites
    -0.77
    سباب
    -0.76
     createContext
    -0.75
     विभ
    -0.75
    POSITIVE LOGITS
     impose
    2.88
     imposed
    2.70
     dictate
    2.59
     imposing
    2.53
     imposition
    2.50
     imposes
    2.41
    dict
    2.33
     dict
    2.30
    imposed
    2.23
    impose
    2.20
    Activations Density 0.050%

    No Known Activations