© 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. 22-GEMMASCOPE-RES-131K
    7. 10835
    Prev
    Next
    INDEX
    Explanations

    reduce risk and problems

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

    The neuron highlights words naming harmful or undesirable conditions or risks (e.g. bleeding, spam, thrombogenicity, risk).

    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
    OrUpdate
    -0.98
    tarjetas
    -0.93
    apertura
    -0.91
    ⤵
    -0.83
    isAuth
    -0.82
    Durée
    -0.82
     quivering
    -0.81
     permettra
    -0.80
    损
    -0.79
    𔘓
    -0.79
    POSITIVE LOGITS
     Erzä
    0.91
     avoid
    0.89
    avoid
    0.88
    ہ
    0.84
     избе
    0.83
    ENDS
    0.80
    dhury
    0.79
    ktes
    0.79
    kait
    0.79
     superfí
    0.78
    Activations Density 0.105%

    No Known Activations