© 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. 14061
    Prev
    Next
    INDEX
    Explanations

    data structures and analysis

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

    The neuron flags programming function or method names (e.g. get_dummies, missRanger, drop) in code snippets.

    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
     hidupnya
    -1.20
     evento
    -1.14
     on
    -1.06
     bakom
    -1.05
     victorious
    -1.05
    ;*/
    -1.05
     字体
    -1.05
     ambos
    -1.04
    voirs
    -1.02
    rure
    -1.00
    POSITIVE LOGITS
    1.27
    álise
    1.15
     we
    1.12
     Certains
    1.10
     الشاشة
    1.09
     Lorsque
    1.07
    cluding
    1.06
    cludes
    1.05
     côtes
    1.05
     لأنه
    1.05
    Activations Density 0.014%
    No Known Activations