© 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. 2254
    Prev
    Next
    INDEX
    Explanations

    lock combinations

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

    The neuron fires on numeric tokens and related combinatorial/math terms (e.g. “combination(s),” digits, “numbers,” “position,” etc.), i.e. math‐oriented numeric context.

    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
     Спи
    -0.76
     appetites
    -0.74
     cabecera
    -0.71
    ießen
    -0.70
     rips
    -0.69
     متعلقه
    -0.68
     banners
    -0.68
    изо
    -0.68
    返し
    -0.66
     pirated
    -0.66
    POSITIVE LOGITS
     keypad
    1.63
     lock
    1.52
     codes
    1.39
     code
    1.37
     Lock
    1.30
     door
    1.26
    Codes
    1.21
     combination
    1.20
     код
    1.19
     Codes
    1.16
    Activations Density 0.013%

    No Known Activations