© 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. 10-GEMMASCOPE-RES-131K
    4. 61283
    Prev
    Next
    INDEX
    Explanations

    terms of use

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

    The neuron strongly responds to the “of Use” tokens in legal headings (as in “Terms of 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_10/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
    ↵↵
    -1.73
     sogen
    -1.36
    無い
    -1.31
     Etats
    -1.31
    t
    -1.30
    4
    -1.29
     odpowied
    -1.28
    not
    -1.27
     evitando
    -1.25
     
    -1.24
    POSITIVE LOGITS
     and
    1.91
     a
    1.48
     since
    1.48
     año
    1.47
     are
    1.47
    koala
    1.43
    cún
    1.38
    }});
    1.36
     美容
    1.34
    餃
    1.32
    Activations Density 0.070%

    No Known Activations