© 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. 34268
    Prev
    Next
    INDEX
    Explanations

    programming imports and services

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

    The neuron activates on parts of dotted, code-style identifiers—i.e. segments of fully qualified class or package names.

    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
    uitable
    -1.18
    Regressor
    -1.16
    InSeconds
    -1.13
    $
    -1.12
    вня
    -1.10
    ¡¡¡
    -1.09
     treff
    -1.06
     isolada
    -1.05
    RDD
    -1.04
     wybrać
    -1.04
    POSITIVE LOGITS
     actually
    1.14
     only
    1.09
     esimer
    1.05
     generally
    1.03
    あなたの
    1.02
    もちろん
    1.01
    잎
    0.99
     you
    0.98
     आदि
    0.96
    lenie
    0.95
    Activations Density 0.044%

    No Known Activations