© 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. 10-GEMMASCOPE-RES-131K
    7. 65999
    Prev
    Next
    INDEX
    Explanations

    ing verbs

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

    The neuron detects sentences beginning with methodological action verbs in their gerund (‐ing) form, as commonly used to describe experimental or analytical steps.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     was
    -1.78
    。
    -1.68
     but
    -1.58
    」
    -1.49
    }
    -1.48
    是在
    -1.44
    }
    -1.43
     "
    -1.41
    .”
    -1.34
    が
    -1.34
    POSITIVE LOGITS
     boste
    1.41
    內容簡介
    1.36
     with
    1.36
     from
    1.27
    だったり
    1.25
    ผม
    1.23
    ですかね
    1.21
    푔
    1.20
     khóa
    1.17
     appétit
    1.17
    Activations Density 0.133%

    No Known Activations