© 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. 55647
    Prev
    Next
    INDEX
    Explanations

    terms of use

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

    The neuron fires strongly on legal‐style headings or references to “terms of use” (often paired with “terms and conditions” or similar licensing labels).

    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
     atteint
    -1.06
     aliviar
    -0.94
    ítima
    -0.92
    декс
    -0.91
     geringen
    -0.82
     schöne
    -0.80
     plonge
    -0.80
     résistant
    -0.80
     beträ
    -0.79
     sueldo
    -0.79
    POSITIVE LOGITS
     of
    1.76
     conditions
    1.48
    条件
    1.27
    겟
    1.16
    conditions
    1.16
     Conditions
    1.07
    of
    1.07
    Condition
    1.05
     warunki
    0.99
    Conditions
    0.97
    Activations Density 0.030%

    No Known Activations