© 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. 22-GEMMASCOPE-RES-131K
    7. 70726
    Prev
    Next
    INDEX
    Explanations

    requesting and granting access

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

    The neuron flags “content‐heavy” or unusually informative tokens—i.e. rarer, high-information words rather than common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    իլ
    -0.94
    illés
    -0.85
    rén
    -0.84
     Cid
    -0.81
    優惠
    -0.81
    剧本
    -0.81
    Comput
    -0.78
    onsumsi
    -0.77
     lada
    -0.77
     deliberations
    -0.77
    POSITIVE LOGITS
     curiosity
    1.24
     permission
    1.16
     invites
    0.98
     request
    0.97
     access
    0.97
     summons
    0.96
     scheduled
    0.92
     invite
    0.92
     topics
    0.91
     пригла
    0.91
    Activations Density 0.138%

    No Known Activations