© 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. 34-GEMMASCOPE-RES-131K
    4. 65917
    Prev
    Next
    INDEX
    Explanations

    issuing a statement

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

    The neuron flags occurrences of formal reported speech—i.e. when an entity “said,” “released,” or “in a statement” introduces a quotation or official statement.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     preguntar
    -0.84
     pregunta
    -0.83
    谙
    -0.82
    alele
    -0.81
     紹介
    -0.79
     proponents
    -0.78
    デオ
    -0.77
     joked
    -0.77
     Eto
    -0.76
    }}^{\
    -0.74
    POSITIVE LOGITS
     statement
    6.06
     statements
    4.59
    statement
    4.47
    Statement
    4.25
     Statement
    4.22
     STATEMENT
    3.88
    STATEMENT
    3.72
    statements
    3.39
     Statements
    3.25
    Statements
    3.00
    Activations Density 0.071%

    No Known Activations