© 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. 14567
    Prev
    Next
    INDEX
    Explanations

    actions in progress or states

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

    The neuron is sensitive to dynamic action words in non‐base forms—that is, verbs in their past participle (–ed) or gerund (–ing) forms.

    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
     after
    -1.49
     during
    -1.48
     because
    -1.41
    前は
    -1.30
     when
    -1.24
     epoca
    -1.24
    などなど
    -1.20
     argento
    -1.16
    なども
    -1.13
     تواند
    -1.12
    POSITIVE LOGITS
    alea
    1.34
     huellas
    1.24
     cuja
    1.20
    ほら
    1.20
     cuya
    1.20
    すっ
    1.18
     manguera
    1.18
     agradável
    1.16
     mitigating
    1.16
     I
    1.15
    Activations Density 0.048%

    No Known Activations