© 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. 10-GEMMASCOPE-RES-131K
    7. 131063
    Prev
    Next
    INDEX
    Explanations

    word completions or grammar questions

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

    The neuron is specifically triggered by the present‐participle form “playing,” firing strongly whenever it sees “playing” (and to a lesser extent its immediate context).

    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
     where
    -1.47
     who
    -1.21
     just
    -1.15
    Tento
    -1.10
     зла
    -1.10
     Critique
    -1.09
    ́ng
    -1.08
    ruecos
    -1.07
    lső
    -1.06
    様です
    -1.06
    POSITIVE LOGITS
    }
    1.34
    ificantly
    1.21
    {
    1.16
    既然
    1.14
     since
    1.11
    alisation
    1.09
     
    1.09
     werden
    1.07
    If
    1.03
    atively
    1.03
    Activations Density 0.060%

    No Known Activations