© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12939
    Prev
    Next
    INDEX
    Explanations

    Antimonium Tartaricum, das Unternehmen

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

    The neuron detects Latin scientific names of organisms (genus + species) in the text.

    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
     $)$
    0.68
    })$
    0.64
    $)$.
    0.63
    }))$
    0.60
     $)$.
    0.59
    }")]
    0.58
     scalar
    0.58
    }]$
    0.58
    }})$
    0.58
    scalar
    0.57
    POSITIVE LOGITS
     начало
    0.90
    нение
    0.90
     произведение
    0.79
    тельное
    0.77
    стояние
    0.76
     пространство
    0.75
    ющее
    0.75
     било
    0.75
     новое
    0.74
    шинство
    0.74
    Activations Density 0.048%

    No Known Activations