© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42319
    Prev
    Next
    INDEX
    Explanations

    introducing a situation

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

    This neuron fires on second-person imperatives or commands (e.g. “go away,” “imagine,” “try,” “choose”).

    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
    だったが
    -1.63
     however
    -1.62
     but
    -1.60
    esercito
    -1.59
    </h4>
    -1.55
     a
    -1.45
    でしたが
    -1.39
     therefore
    -1.35
     today
    -1.35
     since
    -1.35
    POSITIVE LOGITS
     uſ
    1.55
     ¡¡
    1.36
     theſe
    1.35
    或
    1.35
     Некоторые
    1.31
     fone
    1.31
     lancement
    1.30
    ")==
    1.30
     désert
    1.29
     ESQ
    1.29
    Activations Density 0.030%

    No Known Activations