© 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. 10-GEMMASCOPE-RES-131K
    7. 58464
    Prev
    Next
    INDEX
    Explanations

    nippy, sniper, Hosni, NIISK

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

    The neuron fires on occurrences of the substring “jni,” i.e. tokens related to JNI references in 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_10/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
     одном
    -2.88
    筚
    -2.70
     woda
    -2.67
    麈
    -2.63
     wody
    -2.53
    怎么可能
    -2.50
    蔸
    -2.50
    蛩
    -2.48
    鬭
    -2.48
    fgaben
    -2.44
    POSITIVE LOGITS
     -
    3.78
    ?"
    3.44
     "
    3.28
     siquiera
    3.00
    WHAT
    2.88
    )
    2.75
     После
    2.66
    看似
    2.52
    This
    2.47
     --
    2.47
    Activations Density 0.020%

    No Known Activations