© 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. 105082
    Prev
    Next
    INDEX
    Explanations

    access to information and systems

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

    phrases about accessing important resources, systems, or data.

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

    The neuron detects mentions of “access to” something—i.e. contexts describing the ability or right to obtain or use a resource (data, money, protocols, etc.).

    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
    _
    -1.53
    .
    -1.33
     to
    -1.27
    を注文
    -1.22
     innych
    -1.20
     tiež
    -1.19
     stället
    -1.19
     zároveň
    -1.19
     essenziale
    -1.18
     or
    -1.17
    POSITIVE LOGITS
     inspirasi
    1.41
     universelle
    1.29
    Ꮺ
    1.27
     vuotta
    1.23
    middels
    1.22
    尔斯
    1.21
    ന്റെ
    1.20
    🧊
    1.18
    ☆☆☆☆
    1.18
     choses
    1.18
    Activations Density 0.088%

    No Known Activations