© 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. 64971
    Prev
    Next
    INDEX
    Explanations

    anonymous javascript functions

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

    The neuron fires on code identifiers for function or method names (e.g. calls like ready(), change(), click(), resize(), afterEach(), 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
    gebraucht
    -1.09
     témoignages
    -1.05
    idated
    -1.04
    РЯ
    -1.04
    bieten
    -1.03
    忽视
    -1.02
    טה
    -1.02
    Ế
    -1.02
    ısını
    -1.02
    üedad
    -1.01
    POSITIVE LOGITS
    -£
    1.09
    で
    1.05
    veau
    1.03
    が
    1.00
    0
    0.99
    は
    0.97
    l
    0.96
     discussion
    0.93
     piace
    0.93
    も
    0.93
    Activations Density 0.004%

    No Known Activations