© 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. 10-GEMMASCOPE-RES-131K
    4. 110924
    Prev
    Next
    INDEX
    Explanations

    ACM publications and awards

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

    the acronym "ACM" (Association for Computing Machinery).

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

    The neuron fires on the acronym “ACM” when it’s used in technical identifiers or codes (e.g. “ACM‐SIG”, “ACM 450”, “ACM-Reference-Format”), i.e. occurrences of “ACM” followed by numbers or suffixes.

    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
    ).
    -3.13
    霂
    -2.77
    )-\
    -2.50
    辚
    -2.47
     epitome
    -2.44
    媗
    -2.30
    ности
    -2.30
    了一
    -2.28
    rinology
    -2.23
    镒
    -2.22
    POSITIVE LOGITS
    羕
    2.81
    ate
    2.81
    ON
    2.77
    t
    2.70
     ersche
    2.64
    勦
    2.36
     brilhante
    2.31
    囝
    2.28
    ができます
    2.27
    刧
    2.27
    Activations Density 0.003%

    No Known Activations