© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14299
    Prev
    Next
    INDEX
    Explanations

    approval

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

    The neuron detects occurrences of the concept of approving or authorizing (i.e. “approval”-related language).

    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
     "
    -2.67
    …
    -2.61
    \\
    -2.45
     -
    -2.36
    ’
    -2.33
    /
    -2.14
     llegan
    -2.06
     …
    -2.05
    霎
    -2.03
     principalmente
    -2.02
    POSITIVE LOGITS
     anún
    2.64
    𓆜
    2.63
     camiset
    2.58
     sprüche
    2.56
    我们
    2.55
     parachoque
    2.55
    CurtirCurtir
    2.47
     valentín
    2.38
     baumwolle
    2.36
    敺
    2.36
    Activations Density 0.007%

    No Known Activations