© 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. 35241
    Prev
    Next
    INDEX
    Explanations

    keyword followed by colon or preposition

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

    The neuron detects publication‐related metadata markers (like ISBN entries, copyright notices, subscription prompts, etc.).

    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
    ográfica
    -1.05
    任何
    -1.02
     any
    -1.02
    都说
    -1.01
    These
    -1.01
     Schauspielerin
    -1.00
     voetballer
    -1.00
    >
    -0.98
     וכן
    -0.97
    叁
    -0.96
    POSITIVE LOGITS
     viktigt
    0.99
    やろ
    0.94
     няколко
    0.94
    นะคะ
    0.92
     budú
    0.91
    מונות
    0.91
    alleria
    0.91
    輦
    0.88
    だろ
    0.88
    BFF
    0.88
    Activations Density 0.000%

    No Known Activations