© 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. 73698
    Prev
    Next
    INDEX
    Explanations

    claims and identity tokens

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

    The neuron activates on technical security‐ and authentication‐related terms—especially words having to do with tokens, cookies, transport, and security in federation or identity contexts.

    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
    サン
    -0.75
    ühungen
    -0.74
     thủ
    -0.72
    Gain
    -0.72
    हे
    -0.71
    ataly
    -0.70
    制
    -0.68
    ++];
    -0.66
     Witch
    -0.66
    rawtypes
    -0.66
    POSITIVE LOGITS
     claim
    1.05
     Claims
    1.05
     claims
    1.02
     issuing
    0.99
    claim
    0.97
     Claim
    0.95
     issued
    0.94
    claims
    0.93
     issuance
    0.89
     claiming
    0.88
    Activations Density 0.041%

    No Known Activations