© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9067
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates whenever the word “character” appears.

    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
    char
    0.75
    all
    0.74
     caminho
    0.74
     Jardim
    0.71
    3
    0.70
    5
    0.70
    habitat
    0.69
    ay
    0.69
    harmonic
    0.68
     beş
    0.67
    POSITIVE LOGITS
    ご連絡
    0.83
    ついて
    0.82
     incineration
    0.77
     Allowance
    0.76
     consents
    0.75
    つま
    0.75
     advancements
    0.73
    }}^{(\
    0.73
    俵
    0.73
     decommission
    0.71
    Activations Density 0.000%

    No Known Activations