© 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. 34-GEMMASCOPE-RES-131K
    7. 97848
    Prev
    Next
    INDEX
    Explanations

    if a / if you

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

    The neuron fires on the conditional “If” clauses commonly found in software license boilerplate.

    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
     if
    -1.20
     people
    -1.19
     that
    -1.18
     many
    -1.18
     can
    -1.17
     those
    -1.15
     their
    -1.09
     all
    -1.09
     know
    -1.08
     enables
    -1.06
    POSITIVE LOGITS
    ]=>
    1.28
    %',
    1.10
    )].
    1.04
    ****/
    1.04
    .'</
    1.02
    ***/
    1.02
    ]_
    1.00
    believe
    0.99
    ENSITY
    0.99
     صفحة
    0.99
    Activations Density 0.035%

    No Known Activations