© 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. 14062
    Prev
    Next
    INDEX
    Explanations

    software version support lifecycle

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

    The neuron activates on occurrences of “release(s),” especially in software or version‐announcement contexts.

    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
     female
    -1.20
     bosques
    -1.19
    labilir
    -1.16
    录取
    -1.12
     kwenye
    -1.12
     women
    -1.09
     گیاه
    -1.06
     hongos
    -1.04
    餚
    -1.01
    enetrable
    -1.00
    POSITIVE LOGITS
    ᾿
    1.30
     seguirá
    1.21
     will
    1.17
     continuará
    1.16
    BoxShadow
    1.12
     until
    1.08
     pensent
    1.06
     TÉ
    1.06
    ffiche
    1.05
     العالمية
    1.05
    Activations Density 0.061%

    No Known Activations