© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113563
    Prev
    Next
    INDEX
    Explanations

    conditional clauses

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

    conditional statements, particularly the word "if" at the beginning of conditional clauses.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on conditional “if” clauses, especially when they involve numeric values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -1.38
     was
    -1.34
    </sup>
    -1.32
     diſ
    -1.19
     lorsque
    -1.15
    韭
    -1.14
    一旁
    -1.13
    lní
    -1.13
    是要
    -1.13
     citroen
    -1.12
    POSITIVE LOGITS
     through
    1.46
    Beskrivelse
    1.30
     elevada
    1.21
     velikost
    1.21
    Loai
    1.20
    最大の
    1.15
    ungkin
    1.15
    Ilustra
    1.14
    Regardless
    1.13
    emporio
    1.13
    Activations Density 0.094%

    No Known Activations