© 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. 98265
    Prev
    Next
    INDEX
    Explanations

    whether it works well

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

    The neuron activates on occurrences of the verb “work” (e.g. “work,” “works,” etc.).

    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
    錞
    -1.73
     ſch
    -1.67
    驺
    -1.65
    цією
    -1.64
     إنتاج
    -1.64
    壜
    -1.63
     放題
    -1.60
    ◆◆
    -1.58
    糶
    -1.55
    gunas
    -1.54
    POSITIVE LOGITS
    .
    2.09
    }:
    1.73
    ?”
    1.70
    .”
    1.64
    ):
    1.63
    );
    1.52
    ");
    1.49
     таке
    1.48
     when
    1.47
    ”,
    1.47
    Activations Density 0.047%

    No Known Activations