© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68584
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

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

    This neuron detects numeric conversions and casts in code (e.g. parseInt, int, str, String calls and their numeric arguments).

    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
     سایر
    -1.34
     etc
    -1.29
     again
    -1.28
     other
    -1.21
     and
    -1.19
     andere
    -1.14
    ariConfig
    -1.13
    漑
    -1.10
     innych
    -1.09
    起来了
    -1.07
    POSITIVE LOGITS
     пишет
    1.07
    ://"
    1.07
     КА
    1.06
     olhando
    1.06
    クマ
    1.05
     anklicken
    1.05
     Ви
    1.04
    Accordingly
    1.01
     dringend
    1.01
     tilgjenge
    1.00
    Activations Density 0.012%

    No Known Activations