© 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. 14518
    Prev
    Next
    INDEX
    Explanations

    creating directories

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

    The neuron fires on directory‐creation calls (e.g. “mkdir” with its flags/options).

    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
    for
    -1.45
    B
    -1.34
    L
    -1.29
    man
    -1.28
    A
    -1.27
    N
    -1.27
    J
    -1.25
    only
    -1.22
    m
    -1.19
    大部分
    -1.16
    POSITIVE LOGITS
    立派
    1.44
    niť
    1.41
     hermosas
    1.30
    héro
    1.24
    🪜
    1.21
    bánh
    1.21
    ֯
    1.21
     lindas
    1.20
    
    1.18
    França
    1.16
    Activations Density 0.002%

    No Known Activations