© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 11652
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and quotes

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

    This neuron activates on tokens that are part of quoted string literals (e.g. text inside single or double quotes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ''}
    0.93
    ;}
    0.85
     ""}
    0.85
    ";}
    0.80
    .}
    0.79
    "}
    0.79
    ();}
    0.77
     '}
    0.72
     ",")
    0.72
    "}}
    0.72
    POSITIVE LOGITS
    があって
    0.63
    over
    0.60
     خوبی
    0.57
    mut
    0.56
     Doug
    0.56
    代理
    0.55
    Cover
    0.53
    PROPERTY
    0.52
    ضرب
    0.52
     Debbie
    0.52
    Activations Density 0.005%

    No Known Activations