© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2132
    Prev
    Next
    INDEX
    Explanations

    fprintf, table, compass, from, empresa

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

    The neuron sharply responds to the past-tense form “was.”

    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_24_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
    }$}
    0.75
     ڪ
    0.73
     Evaluación
    0.72
     Antônio
    0.69
    }}}{\
    0.68
     Vázquez
    0.68
     Gutiérrez
    0.66
    }{\
    0.66
    с
    0.66
    S
    0.65
    POSITIVE LOGITS
    مانی
    0.82
    ዴት
    0.79
     frein
    0.78
     प्रमाणात
    0.78
    مان
    0.77
    亢
    0.77
     hollywood
    0.76
     tende
    0.76
     পারছে
    0.76
     retarded
    0.75
    Activations Density 0.000%

    No Known Activations