© 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. 72145
    Prev
    Next
    INDEX
    Explanations

    variable assignment and operations

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

    The neuron flags object‐oriented member access patterns (instances of “object.property” or “object.method”) in the code.

    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
     étrang
    -1.39
     bluz
    -1.31
    jadinya
    -1.31
     bluza
    -1.30
     sezonu
    -1.26
    puede
    -1.24
    daad
    -1.19
    dä
    -1.18
    متن
    -1.18
     salonu
    -1.17
    POSITIVE LOGITS
    u
    1.34
    y
    1.31
    M
    1.27
    H
    1.26
    K
    1.25
    C
    1.25
    v
    1.23
    F
    1.22
    f
    1.20
    V
    1.20
    Activations Density 0.008%

    No Known Activations