© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65924
    Prev
    Next
    INDEX
    Explanations

    database access methods

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

    This neuron detects calls to record‐fetching or data‐loading methods (e.g. find, load, get, FirstOrDefault, FindBy) used to retrieve model or database objects.

    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
     finally
    -1.05
     der
    -1.01
     \&
    -1.00
    ḏ
    -1.00
     Startseite
    -1.00
    raphe
    -1.00
     still
    -0.97
     “
    -0.96
    福祉
    -0.95
     Det
    -0.94
    POSITIVE LOGITS
    möglichen
    1.29
    着脸
    1.12
    Siapa
    1.12
    توضیحات
    1.11
    Bisa
    1.09
    אם
    1.09
    אני
    1.08
    cách
    1.08
     or
    1.07
    spania
    1.06
    Activations Density 0.001%

    No Known Activations