© 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. 50182
    Prev
    Next
    INDEX
    Explanations

    assigning result or ans

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

    The neuron activates on numeric literals (integer constants) in code.

    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
    agri
    -0.90
    ğından
    -0.88
    ieR
    -0.86
    Ӫ
    -0.84
    ໋
    -0.84
    efined
    -0.83
     coussin
    -0.82
    Empereur
    -0.82
    payed
    -0.82
     dinosaurio
    -0.81
    POSITIVE LOGITS
    me
    1.23
    val
    1.01
    Val
    1.00
    ent
    0.98
    ni
    0.97
    far
    0.95
    ne
    0.93
    Value
    0.93
    Continue
    0.91
    Gr
    0.90
    Activations Density 0.010%

    No Known Activations