© 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. 104407
    Prev
    Next
    INDEX
    Explanations

    input values and attributes

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

    The neuron fires on HTML input (and similar) attributes that assign default text—e.g. “placeholder” or “value.”

    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
     también
    -1.13
     também
    -1.05
    กับ
    -1.04
     definição
    -1.02
    Quiénes
    -1.02
    MediaStore
    -0.99
     convite
    -0.99
    Cómo
    -0.97
     its
    -0.97
     مؤرشف
    -0.96
    POSITIVE LOGITS
    𝘩
    1.05
    zionato
    0.98
     bestehende
    0.96
    Inno
    0.95
    ificação
    0.94
    飩
    0.93
    glGet
    0.92
    このように
    0.91
    tizado
    0.90
    ェ
    0.90
    Activations Density 0.001%

    No Known Activations