© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14218
    Prev
    Next
    INDEX
    Explanations

    variable assignment with tokens

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

    The neuron flags variable names and tokens related to authentication credentials (e.g. “token,” “jwt,” “apiKey,” “TICKET,” 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_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
     depending
    -1.17
     for
    -1.13
     is
    -1.12
    munt
    -1.09
     мод
    -1.07
     τὰ
    -1.03
     
    -1.03
      
    -1.03
     /
    -1.01
     ciclismo
    -1.01
    POSITIVE LOGITS
     pastillas
    1.23
     camas
    1.20
    Domaine
    1.16
    遶
    1.14
    dateien
    1.12
    ࣪
    1.11
     soggior
    1.11
    ְּ
    1.06
    𓏸
    1.05
     INSTR
    1.05
    Activations Density 0.021%

    No Known Activations