© 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. 11295
    Prev
    Next
    INDEX
    Explanations

    verbs followed by direct objects or descriptions

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

    The neuron activates on verbs that express obtaining or acquiring something.

    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
     there
    -1.71
    还有
    -1.48
    E
    -1.42
    :
    -1.40
     other
    -1.31
     on
    -1.29
     take
    -1.24
    還有
    -1.23
    }
    -1.22
    cesta
    -1.20
    POSITIVE LOGITS
     laquelle
    1.44
    Läh
    1.29
     sollte
    1.23
     adatt
    1.23
    sible
    1.22
    黑色的
    1.20
    jící
    1.18
     piaci
    1.18
     incluse
    1.18
    bleven
    1.16
    Activations Density 0.285%

    No Known Activations